financial-modeling-prep-mcp-server

v2.6.8

Published

12 days ago

Model Context Protocol server for Financial Modeling Prep (FMP) API, exposing 250+ tools for financial data, market insights, and analysis.

Financial Modeling Prep MCP (Model Context Protocol) Server

A Model Context Protocol (MCP) implementation for Financial Modeling Prep, enabling AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights.

Quick Start

Choose your deployment option:

🚀 Option 1: Use Our Hosted Instance (Fastest)

No installation required!

Get FMP API Key: Sign up at FMP
Connect to our endpoint: https://financial-modeling-prep-mcp-server-production.up.railway.app/mcp
Provide API key in session configuration
Start using 5 meta-tools to load toolsets dynamically

Available via:

Direct HTTP connection (recommended)
MCP registries like Smithery.ai, Glama.ai, Contexaai.com

Example session config:

{
  "FMP_ACCESS_TOKEN": "your_fmp_api_key_here"
}

🏠 Option 2: Self-Host Your Own Instance (Full Control)

Choose your mode and deploy:

NPM Installation:

npm install -g financial-modeling-prep-mcp-server
export FMP_ACCESS_TOKEN=your_token_here
export DYNAMIC_TOOL_DISCOVERY=true  # or choose static/legacy
fmp-mcp

Docker (build from source):

git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server
cd Financial-Modeling-Prep-MCP-Server
docker build -t fmp-mcp-server .
docker run -p 8080:8080 \
  -e FMP_ACCESS_TOKEN=your_token_here \
  -e DYNAMIC_TOOL_DISCOVERY=true \
  fmp-mcp-server

See Installation Methods for detailed self-hosting options.

Features

Powered by Toolception: Built on toolception for robust server orchestration and dynamic tool management
5 Meta-Tools in Dynamic Mode: enable_toolset, disable_toolset, list_toolsets, describe_toolset, list_tools
Comprehensive Coverage: Access to 253+ financial tools across 24 categories
Flexible Deployment: Use our hosted instance or self-host with full control
Tool Set Filtering: Load only the tools you need to reduce complexity and improve performance
Dynamic Tool Loading: Runtime enable/disable of tool categories via meta-tools
Real-time Data: Live stock quotes, market data, and financial information
Financial Statements: Income statements, balance sheets, cash flow statements, and financial ratios
Market Analysis: Technical indicators, analyst estimates, and market performance metrics
Economic Data: Treasury rates, economic indicators, and macroeconomic information
Alternative Data: ESG scores, insider trading, congressional trading, and social sentiment

Deployment Options

This server can be used in two ways:

📡 Using Our Hosted Instance (Recommended for Quick Start)

Direct HTTP Endpoint:

https://financial-modeling-prep-mcp-server-production.up.railway.app/mcp

Also available through MCP registries:

Smithery.ai: View on Smithery
Glama.ai, Contexaai.com (see Registries section)

Configuration:

Runs in dynamic mode (5 meta-tools: enable_toolset, disable_toolset, list_toolsets, describe_toolset, list_tools)
Requires FMP API key in session configuration (not server environment)
No server-side setup needed - just connect and use

🏠 Self-Hosting Your Own Instance (Full Control)

Deploy your own instance for complete control:

Choose any mode: Dynamic, Static, or Legacy
Configure via: Environment variables or CLI arguments
Deployment options: NPM, Docker, or from source
See Installation Methods below

Server Architecture

This MCP server leverages toolception - a dynamic MCP server toolkit for runtime toolset management with Fastify transport and meta-tools. Toolception provides complete server orchestration including HTTP transport, session management, and tool lifecycle.

Key Features:

Powered by Toolception: Uses toolception for server orchestration and dynamic tool management
Client-level Caching: Toolception's ClientResourceCache maintains isolated sessions per client with LRU/TTL eviction
Session Isolation: Each client gets their own MCP server instance with independent tool state
Stateful Management: Sessions maintain their state across multiple requests via toolception's session management
Mode Enforcement: Server-level configurations can override session-level settings
HTTP-based Protocol: Communicates via HTTP with JSON-RPC formatted messages using Fastify transport
Dynamic Tool Management: Tools can be loaded/unloaded at runtime per session using toolception's DynamicToolManager

Transport & Client Compatibility

Important: This server uses HTTP/SSE transport only (no stdio). See compatibility notes below.

| Client | Support | How to Connect | |--------|---------|----------------| | Claude.ai | Yes | Settings > Connectors > Add remote server | | Claude Desktop | Yes | Settings > Connectors (NOT claude add or config.json) | | Claude Mobile | Yes | Uses servers added via claude.ai | | Smithery/Glama | Yes | Via registry with server card | | Custom HTTP | Yes | Include mcp-client-id header |

Claude Desktop users: Do NOT use claude add <url> or edit claude_desktop_config.json - these expect stdio transport. Instead, add as a remote server via Settings > Connectors.

See Anthropic's Remote MCP Server Guide.

Request Flow:

Client Request → HTTP POST to / endpoint
Session Management → Toolception creates or retrieves session based on client ID (caching via ClientResourceCache)
Mode Resolution → Server determines operational mode (Dynamic/Static/Legacy)
Tool Registration → Toolception's ModuleResolver lazy-loads tools based on resolved mode
Request Processing → MCP request is processed with available tools via toolception's orchestrator
Response → JSON-RPC response sent back to client

Available HTTP Endpoints:

POST /mcp - Main MCP protocol endpoint (JSON-RPC formatted messages)
- Requires session initialization - see Session Management
GET /ping - Simple ping endpoint (returns {"status": "ok"})
GET /healthcheck - Comprehensive health check endpoint
GET /.well-known/mcp/server-card.json - MCP server card for auto-discovery (SEP-1649)

Configuration & Mode Enforcement

The server supports multiple configuration methods with a clear precedence hierarchy to ensure predictable behavior.

Understanding Server Modes

The server supports three operational modes. The mode you use depends on your deployment scenario:

Using Our Hosted Instance (Railway)

Fixed Mode: Dynamic mode (5 meta-tools)
Configuration: Pass FMP_ACCESS_TOKEN in session config
Use Case: Quick start without deployment
Access: Direct HTTP or via MCP registries

Self-Hosting Your Own Instance

Your Choice: Select any mode via environment variables or CLI arguments
Configuration: Set at server startup
Use Case: Full control over tools and configuration

Available Modes

1. 🔀 Dynamic Mode (`DYNAMIC_TOOL_DISCOVERY=true`)

Starts with only 5 meta-tools:

enable_toolset - Enable a toolset by name
disable_toolset - Disable a toolset by name
list_toolsets - List available toolsets with active status
describe_toolset - Describe a toolset with details and tools
list_tools - List currently registered tool names

When to Use:

✅ Using our hosted instance (default)
✅ Building flexible workflows where tool needs change
✅ Minimizing initial overhead
✅ Multi-tenant deployments where users need different tools

Our Hosted Instance: This is the default mode

Self-Hosted: Set via DYNAMIC_TOOL_DISCOVERY=true or --dynamic-tool-discovery

2. 🔧 Static Mode (`FMP_TOOL_SETS=search,company,quotes`)

Pre-loads specific toolsets at session creation. All specified tools available immediately.

When to Use:

✅ Self-hosted with known, consistent tool requirements
✅ Predictable usage patterns
✅ Faster tool access (no runtime loading)

Our Hosted Instance: Not available (we use dynamic mode)

Self-Hosted: Set via FMP_TOOL_SETS=search,company,quotes or --fmp-tool-sets=search,company,quotes

3. 📚 Legacy Mode (no specific configuration)

Loads all 253+ tools at session creation. Maximum compatibility with all features.

When to Use:

✅ Self-hosted with full feature access requirements
✅ No configuration complexity needed
✅ Not concerned about initial load time

Our Hosted Instance: Not available (we use dynamic mode)

Self-Hosted: Default when no mode is configured, or set DYNAMIC_TOOL_DISCOVERY=false

Configuration Precedence (Self-Hosted Only)

When self-hosting, configuration follows this strict precedence hierarchy:

🥇 CLI Arguments (highest priority)
   ↓
🥈 Environment Variables
   ↓
🥉 Session Configuration (lowest priority)

Note: Our hosted instance mode configuration is fixed to dynamic tool exploration and cannot be changed via session config.

⚠️ Important Mode Enforcement Behavior (Self-Hosted)

When server-level configurations are set (CLI arguments or environment variables), they override all session-level configurations for ALL sessions. This ensures consistent behavior across the entire server instance.

Example Override Scenario:

# Server started with CLI argument
npm run dev -- --dynamic-tool-discovery

# ALL session requests will use Dynamic Mode, regardless of session config
# Session config like {"FMP_TOOL_SETS": "search,company"} will be IGNORED

Configuration Methods:

CLI Arguments (Server-level - overrides everything)

npm run dev -- --fmp-token=TOKEN --dynamic-tool-discovery
npm run dev -- --fmp-token=TOKEN --fmp-tool-sets=search,company,quotes
npm run dev -- --port=4000 --fmp-token=TOKEN

Environment Variables (Server-level - overrides session configs)

DYNAMIC_TOOL_DISCOVERY=true npm run dev
FMP_TOOL_SETS=search,company,quotes npm run dev

Session Configuration (Session-level - via HTTP query parameter)

# Base64 encoded JSON config in query parameter
curl -X POST "http://localhost:8080/mcp?config=eyJEWU5BTUlDX1RPT0xfRElTQ09WRVJZIjoidHJ1ZSJ9"

⚠️ Configuration Warnings

Server-level modes are GLOBAL: They affect all sessions on the server instance
Session configs are IGNORED when server-level modes are active
No mixing: You cannot have different modes for different sessions when server-level enforcement is active
Restart required: Changing server-level configurations requires server restart

Selective Tool Loading

While MCP clients can filter tools automatically, large tool sets may impact performance. To optimize your experience, you can specify which tool categories to load instead of loading all 253 tools at once:

Available Tool Sets

| Tool Set | ---------------------- | search | company | quotes | statements | calendar | charts | news | analyst | market-performance | insider-trades | institutional | indexes | economics | crypto | forex | commodities | etf-funds | esg | technical-indicators | senate | sec-filings | earnings | dcf | bulk | Description | Example Tools | | ---------------------- | ----------------------------------------------------- | | Search & Directory | Search stocks, company lookup, symbol directories | | Company Profile & Info | Company profiles, executives, employee count | | Real-time Quotes | Live stock prices, market data, price changes | | Financial Statements | Income statements, balance sheets, cash flow, ratios | | Financial Calendar | Earnings calendar, dividends, IPOs, stock splits | | Price Charts & History | Historical prices, technical charts, market movements | | Financial News | Market news, press releases, financial articles | | Analyst Coverage | Price targets, ratings, analyst estimates | | Market Performance | Sector performance, gainers, losers, most active | | Insider Trading | Corporate insider activity, ownership changes | | Institutional Holdings | 13F filings, fund holdings, institutional ownership | | Market Indexes | S&P 500, NASDAQ, Dow Jones, index constituents | | Economic Data | Treasury rates, GDP, inflation, economic indicators | | Cryptocurrency | Crypto prices, market data, digital assets | | Foreign Exchange | Currency pairs, exchange rates, forex data | | Commodities | Gold, oil, agricultural products, futures | | ETFs & Mutual Funds | Fund holdings, performance, fund information | | ESG & Sustainability | Environmental, social, governance ratings | | Technical Indicators | RSI, SMA, EMA, MACD, Bollinger Bands | | Government Trading | Congressional and Senate trading disclosures | | SEC Filings | 10-K, 10-Q, 8-K filings, regulatory documents | | Earnings & Transcripts | Earnings reports, call transcripts | | DCF Valuation | Discounted cash flow models, valuations | | Bulk Data | Large-scale data downloads for analysis |

Dynamic Toolset Management (BETA)

🚧 This feature is currently in BETA. API and behavior may change in future versions.

The Dynamic Toolset Management feature allows you to enable and disable tool categories at runtime instead of pre-configuring them at startup. This provides more flexibility and can help optimize performance by loading only the tools you need when you need them.

How It Works

When dynamic toolset management is enabled, each session starts with only 5 meta-tools:

enable_toolset - Enable a toolset by name
disable_toolset - Disable a toolset by name (state only)
list_toolsets - List available toolsets with active status and definitions
describe_toolset - Describe a toolset with definition, active status and tools
list_tools - List currently registered tool names (best effort)

AI assistants can then use these meta-tools to dynamically load and unload specific tool categories as needed for different tasks within their session.

Configuration Options

Server-Level Configuration (Affects All Sessions)

Command Line Arguments:

# Enable dynamic toolset management for all sessions
npm run dev -- --fmp-token=YOUR_TOKEN --dynamic-tool-discovery

# Production deployment
node dist/index.js --fmp-token=YOUR_TOKEN --dynamic-tool-discovery

Environment Variables:

# Set environment variable
export DYNAMIC_TOOL_DISCOVERY=true
export FMP_ACCESS_TOKEN=YOUR_TOKEN
npm run dev

# Or inline
DYNAMIC_TOOL_DISCOVERY=true FMP_ACCESS_TOKEN=YOUR_TOKEN npm start

Docker:

# docker-compose.yml
version: "3.8"
services:
  fmp-mcp:
    build: .
    ports:
      - "8080:8080"
    environment:
      - FMP_ACCESS_TOKEN=YOUR_FMP_ACCESS_TOKEN
      - DYNAMIC_TOOL_DISCOVERY=true # Enable for all sessions

Session-Level Configuration (When No Server Override)

When no server-level dynamic mode is set, individual sessions can request dynamic mode:

# Base64 encode: {"DYNAMIC_TOOL_DISCOVERY":"true"}
CONFIG_BASE64=$(echo -n '{"DYNAMIC_TOOL_DISCOVERY":"true"}' | base64)
curl -X POST "http://localhost:8080/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize",...}'

Example Workflow

Start server with dynamic mode:
```
DYNAMIC_TOOL_DISCOVERY=true npm start
```

AI assistant initializes session and gets meta-tools:

// Response includes only 5 meta-tools:
{
  "tools": [
    { "name": "enable_toolset", "description": "Enable a toolset by name" },
    { "name": "disable_toolset", "description": "Disable a toolset by name (state only)" },
    { "name": "list_toolsets", "description": "List available toolsets with active status and definitions" },
    { "name": "describe_toolset", "description": "Describe a toolset with definition, active status and tools" },
    { "name": "list_tools", "description": "List currently registered tool names (best effort)" }
  ]
}

AI assistant enables needed toolsets:

// Enable search toolset
{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"enable_toolset","arguments":{"toolset":"search"}}}

// Enable quotes toolset
{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"enable_toolset","arguments":{"toolset":"quotes"}}}

AI assistant uses the enabled tools:

// Now can use search and quotes tools
{"jsonrpc":"2.0","id":4,"method":"tools/call","params":{"name":"searchSymbol","arguments":{"query":"AAPL"}}}
{"jsonrpc":"2.0","id":5,"method":"tools/call","params":{"name":"getQuote","arguments":{"symbol":"AAPL"}}}

AI assistant can disable unused toolsets:

{
  "jsonrpc": "2.0",
  "id": 6,
  "method": "tools/call",
  "params": {
    "name": "disable_toolset",
    "arguments": { "toolset": "search" }
  }
}

Benefits

Performance: Start faster with fewer tools loaded initially per session
Flexibility: Load only the tools needed for current tasks
Resource Efficiency: Reduce memory usage by disabling unused toolsets per session
Task-Oriented: Perfect for AI assistants that work on specific financial analysis tasks
Session Isolation: Each session can have different active toolsets

Usage

Registries

For production environments, you can use this MCP server through various registries that provide hosted and managed MCP servers:

MCP Registry

The Financial Modeling Prep MCP Server is available through the official Model Context Protocol Registry, providing standardized installation and discovery for AI platforms.

Quick Start from Registry

NPM Installation:

npm install financial-modeling-prep-mcp-server
npx fmp-mcp --fmp-token=YOUR_TOKEN

Docker (build from source):

git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server
cd Financial-Modeling-Prep-MCP-Server
docker build -t fmp-mcp-server .
docker run -p 8080:8080 -e FMP_ACCESS_TOKEN=YOUR_TOKEN fmp-mcp-server

From Source:

git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server
cd Financial-Modeling-Prep-MCP-Server
npm install && npm run build
npm start -- --fmp-token=YOUR_TOKEN

Registry Installation Methods

The server supports multiple installation methods through the MCP Registry:

| Method | Command | Best For | | ---------- | ----------------------------------------------------------------- | ------------------------------- | | NPM | npm install financial-modeling-prep-mcp-server | Development and local testing | | Docker | git clone && docker build -t fmp-mcp-server . | Production deployments | | Source | git clone && npm install | Customization and contributions |

Quick Start Guide for Registry Users

1. Choose Your Installation Method:

# Option A: NPM (recommended for development)
npm install financial-modeling-prep-mcp-server
npx fmp-mcp --fmp-token=YOUR_TOKEN

# Option B: Docker (recommended for production)
git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server
cd Financial-Modeling-Prep-MCP-Server
docker build -t fmp-mcp-server .
docker run -p 8080:8080 -e FMP_ACCESS_TOKEN=YOUR_TOKEN fmp-mcp-server

# Option C: From source (for customization)
git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server
cd Financial-Modeling-Prep-MCP-Server && npm install && npm run build
npm start -- --fmp-token=YOUR_TOKEN

2. Get Your FMP API Token:

Visit Financial Modeling Prep
Sign up for a free account
Copy your API key from the dashboard

3. Test the Installation:

# Health check
curl http://localhost:8080/healthz

# List available tools
curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

4. Connect to Your AI Platform:

Configure your MCP client to connect to http://localhost:8080/mcp
Use the server in your AI conversations for financial analysis
Refer to your platform's MCP integration documentation

AI Platform Integration

This server uses HTTP/SSE transport and is compatible with platforms that support remote MCP servers:

Claude (claude.ai, Desktop, Mobile) - Add via Settings > Connectors as a remote server. See Anthropic's guide.
Smithery.ai / Glama.ai / Contexaai - Supported via MCP registries
Custom Applications - Use MCP SDK with HTTP transport

Note: This server does NOT support stdio transport. Do not use claude add <url> or claude_desktop_config.json - these methods expect stdio.

Installation Methods

The Financial Modeling Prep MCP Server supports multiple installation methods to fit different deployment scenarios and development workflows.

NPM Installation

Prerequisites:

Node.js ≥25.3.0
NPM or Yarn package manager
Financial Modeling Prep API token

Install globally:

npm install -g financial-modeling-prep-mcp-server
fmp-mcp --fmp-token=YOUR_TOKEN

Install locally in project:

npm install financial-modeling-prep-mcp-server
npx fmp-mcp --fmp-token=YOUR_TOKEN

With configuration options:

# Custom port and dynamic mode
npx fmp-mcp --fmp-token=YOUR_TOKEN --port=4000 --dynamic-tool-discovery

# Static toolset mode
npx fmp-mcp --fmp-token=YOUR_TOKEN --fmp-tool-sets=search,company,quotes

Docker Installation

Prerequisites:

Docker Engine
Git
Financial Modeling Prep API token

Build the Docker image:

git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server
cd Financial-Modeling-Prep-MCP-Server
docker build -t fmp-mcp-server .

Basic Docker run:

docker run -p 8080:8080 \
  -e FMP_ACCESS_TOKEN=YOUR_TOKEN \
  fmp-mcp-server

With custom configuration:

# Dynamic mode with custom port
docker run -p 4000:4000 \
  -e FMP_ACCESS_TOKEN=YOUR_TOKEN \
  -e PORT=4000 \
  -e DYNAMIC_TOOL_DISCOVERY=true \
  fmp-mcp-server

# Static toolset mode
docker run -p 8080:8080 \
  -e FMP_ACCESS_TOKEN=YOUR_TOKEN \
  -e FMP_TOOL_SETS=search,company,quotes \
  fmp-mcp-server

Docker Compose:

version: "3.8"
services:
  fmp-mcp:
    build: .
    ports:
      - "8080:8080"
    environment:
      - FMP_ACCESS_TOKEN=YOUR_FMP_ACCESS_TOKEN
      - PORT=8080
      # Optional: Choose server mode
      - DYNAMIC_TOOL_DISCOVERY=true
      # OR: - FMP_TOOL_SETS=search,company,quotes
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/healthz"]
      interval: 30s
      timeout: 10s
      retries: 3

Source Installation

Prerequisites:

Node.js ≥25.3.0
Git
NPM or Yarn package manager
Financial Modeling Prep API token

Clone and build:

# Clone repository
git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server.git
cd Financial-Modeling-Prep-MCP-Server

# Install dependencies
npm install

# Build TypeScript
npm run build

# Start server
npm start -- --fmp-token=YOUR_TOKEN

Development mode:

# Run with hot reload
npm run dev -- --fmp-token=YOUR_TOKEN

# Run tests
npm test

# Run with coverage
npm run test:coverage

# Verify installation methods
npm run verify:installation

# Type checking
npm run typecheck

Custom build configuration:

# Build with specific target
npx tsc --target ES2022

# Build and watch for changes
npx tsc --watch

# Clean build
rm -rf dist && npm run build

Environment Variables

These apply when self-hosting your own instance. Our hosted instance has fixed configuration.

| Variable | Description | Self-Host Default | Our Hosted Instance | Notes | | ------------------------ | --------------------------------- | ----------------- | ------------------- | ----- | | FMP_ACCESS_TOKEN | Financial Modeling Prep API token | - | Not set | Our hosted: Pass via session config | | PORT | Server port | 8080 | Railway-managed | | | DYNAMIC_TOOL_DISCOVERY | Enable dynamic toolset mode | false | true (fixed) | Our hosted: Always dynamic mode | | FMP_TOOL_SETS | Static toolsets (comma-separated) | - | Not applicable | Our hosted: Dynamic mode only | | NODE_ENV | Node.js environment | development | production | |

Deployment Scenarios:

Using Our Hosted Instance (Railway):

✅ No environment variables needed on your end
✅ Pass FMP_ACCESS_TOKEN in session config
✅ Dynamic mode enabled by default
✅ Access via direct HTTP or MCP registries

Self-Hosting Your Own Instance:

# Example: Dynamic mode with server-level API key
export FMP_ACCESS_TOKEN=your_token_here
export DYNAMIC_TOOL_DISCOVERY=true
export PORT=8080
npm start

# Example: Static mode with specific toolsets
export FMP_ACCESS_TOKEN=your_token_here
export FMP_TOOL_SETS=search,company,quotes
npm start

# Example: Legacy mode (all tools)
export FMP_ACCESS_TOKEN=your_token_here
npm start

Verification

After installation, verify the server is working:

Health check:

curl http://localhost:8080/healthz

MCP capabilities:

curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": {
      "protocolVersion": "2024-11-05",
      "clientInfo": {"name": "test", "version": "1.0.0"},
      "capabilities": {}
    }
  }'

List available tools:

curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'

Troubleshooting

Common issues and solutions:

Port already in use:

# Use different port
PORT=4000 npm start -- --fmp-token=YOUR_TOKEN

Invalid API token:

# Verify token at https://financialmodelingprep.com/developer/docs
curl "https://financialmodelingprep.com/api/v3/profile/AAPL?apikey=YOUR_TOKEN"

Memory issues with all tools:

# Use dynamic mode or specific toolsets
npm start -- --fmp-token=YOUR_TOKEN --dynamic-tool-discovery

Docker permission issues:

# Run with user permissions
docker run --user $(id -u):$(id -g) -p 8080:8080 \
  -e FMP_ACCESS_TOKEN=YOUR_TOKEN \
  fmp-mcp-server

Smithery.ai

The Financial Modeling Prep MCP Server is listed on Smithery as one way to access our hosted instance.

View on Smithery.ai

Important Update: Smithery Hosting Changes (March 2026)

On March 1st, 2026, Smithery discontinued their free hosting service. As a result:

✅ Our hosted instance is still available - We deployed our own server to Railway and expose it via Smithery
✅ No server setup required - Just connect and provide your FMP API key
❌ No Smithery-hosted version - The server runs on our infrastructure, not Smithery's

Using Our Hosted Instance

Server Configuration:

Mode: Dynamic (5 meta-tools only)
Endpoint: https://financial-modeling-prep-mcp-server-production.up.railway.app/mcp
API Key: You must provide your FMP API key in session configuration

Session Configuration Requirements:

You must pass your FMP API key in the session configuration. The server does not have an API key configured at the environment level.

Example Session Configuration:

{
  "FMP_ACCESS_TOKEN": "your_fmp_api_key_here"
}

Alternative Configurations:

// Explicitly request dynamic mode (already the default)
{
  "FMP_ACCESS_TOKEN": "your_fmp_api_key_here",
  "DYNAMIC_TOOL_DISCOVERY": "true"
}

// Note: Static/Legacy modes are NOT SUPPORTED on our hosted instance
// Server-level configuration overrides session requests
{
  "FMP_ACCESS_TOKEN": "your_fmp_api_key_here",
  "FMP_TOOL_SETS": "search,company,quotes"  // This will be ignored
}

Important Notes:

🔒 Your API key is required - We don't store API keys on the server
🚀 Dynamic mode only - Our instance is configured for dynamic mode
🔧 Meta-tools available - Use them to load toolsets as needed
💡 Session isolation - Your tools and state are isolated from other users

Getting Your FMP API Key

Visit Financial Modeling Prep
Sign up for a free account
Copy your API key from the dashboard
Use it in your session configuration

Want Different Configuration?

If you need static or legacy mode, or want full control over the server configuration:

Self-Host Your Own Instance:

Follow the Installation Methods guide
Choose any mode (dynamic, static, or legacy)
Configure environment variables as needed
Deploy to your preferred platform

Then Register with Smithery (Optional):

Deploy your instance with a public URL
Register the external URL with Smithery (free)
Full configuration control

For Smithery integration documentation, visit smithery.ai/docs.

Glama.ai

Use on Glama.ai

Contexaai.com

Use on Contexaai.com

HTTP Server & Local Development

The server runs as an HTTP server that exposes a Model Context Protocol endpoint. Each request can include session-specific configuration via query parameters.

Basic Server Setup

Local Development:

# Clone and setup
git clone https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server
cd Financial-Modeling-Prep-MCP-Server
npm install
npm run build

# Run in development
FMP_ACCESS_TOKEN=YOUR_TOKEN npm run dev

# Or with CLI arguments
npm run dev -- --fmp-token=YOUR_TOKEN
npm run dev -- --port=4000 --fmp-token=YOUR_TOKEN

Server-Level Mode Configuration

🔐 Server-Level Dynamic Mode (All Sessions Use Dynamic Mode):

# CLI argument (highest priority)
npm run dev -- --fmp-token=YOUR_TOKEN --dynamic-tool-discovery

# Environment variable
DYNAMIC_TOOL_DISCOVERY=true FMP_ACCESS_TOKEN=YOUR_TOKEN npm run dev

🔧 Server-Level Static Mode (All Sessions Use Specified Toolsets):

# CLI argument (highest priority)
npm run dev -- --fmp-token=YOUR_TOKEN --fmp-tool-sets=search,company,quotes

# Environment variable
FMP_TOOL_SETS=search,company,quotes FMP_ACCESS_TOKEN=YOUR_TOKEN npm run dev

📚 Server-Level Legacy Mode (All Sessions Get All Tools):

# Default behavior - no specific configuration
npm run dev -- --fmp-token=YOUR_TOKEN
FMP_ACCESS_TOKEN=YOUR_TOKEN npm run dev

Custom Port Configuration

# Change server port via environment variable
PORT=4000 npm run dev -- --fmp-token=YOUR_TOKEN

# Change server port via CLI argument
npm run dev -- --port=4000 --fmp-token=YOUR_TOKEN

Example System Prompts

The following system prompts are designed to help AI assistants effectively use this MCP server for financial analysis tasks. Choose the appropriate prompt based on your server configuration mode.

For Dynamic Toolset Mode

You are an expert financial analyst AI with access to comprehensive market data tools.

CORE RULES:
- Always use tools for current market data; never rely on outdated information or estimates
- Check conversation history to avoid redundant tool calls
- Provide concise, data-driven responses
- Always include: "This is not financial advice"

DYNAMIC TOOLSET MANAGEMENT:
Your tools are organized into categories ("toolsets") that must be enabled before use.

Available toolsets: search, company, quotes, statements, calendar, charts, news, analyst, market-performance, insider-trades, institutional, indexes, economics, crypto, forex, commodities, etf-funds, esg, technical-indicators, senate, sec-filings, earnings, dcf, bulk

EXECUTION WORKFLOW:
1. DISCOVER: Use list_toolsets to see available toolset categories and their status
2. ENABLE: Use enable_toolset for required categories based on the user's query
3. VERIFY: Use list_tools to confirm the tools you need are available
4. EXECUTE: Call specific tools from enabled toolsets
5. CLEAN UP: Consider disabling unused toolsets when switching to different analysis types

FAILURE PROTOCOL:
If tools fail repeatedly or data is unavailable, state: "I cannot find the requested information with the available tools" and stop attempting.

Begin each analysis by enabling the appropriate toolsets for the user's request.

For Static Toolset Mode

You are an expert financial analyst AI with access to comprehensive market data tools.

CORE RULES:
- Always use tools for current market data; never rely on outdated information or estimates
- Check conversation history to avoid redundant tool calls
- Provide concise, data-driven responses
- Always include: "This is not financial advice"

STATIC TOOLSET CONFIGURATION:
Your tools are pre-loaded and immediately available. All configured toolsets remain active throughout the session.

EXECUTION WORKFLOW:
1. IDENTIFY: Determine which tools from your available toolsets best address the user's query
2. EXECUTE: Call the appropriate tools directly - no toolset management needed
3. ANALYZE: Process the data and provide insights based on the results

TOOL CATEGORIES:
Your available tools span multiple categories including company profiles, financial statements, market quotes, technical analysis, news sentiment, and economic indicators. Use the most relevant tools for each analysis.

FAILURE PROTOCOL:
If tools fail repeatedly or data is unavailable, state: "I cannot find the requested information with the available tools" and stop attempting.

Proceed directly to analysis using your available tools based on the user's request.

Usage Tips

Dynamic Mode: Best for exploratory analysis where tool requirements change frequently. The AI assistant will manage toolsets based on the current task.
Static Mode: Best for consistent, predictable workflows where the same types of analysis are performed repeatedly.
Legacy Mode: Use the Static Mode prompt when all tools are pre-loaded (default configuration).

Human-Friendly Capabilities Prompt

This server provides a human-friendly prompt to list capabilities in one shot.

Name: list_mcp_assets
Output sections: Server Capabilities, Prompts, Tools (mode-aware), Resources (health snapshot), Quick Start
Exposed only as an MCP prompt (no tool alias)

List assets via prompts

# 1) Initialize (example: dynamic mode session)
CONFIG_BASE64=$(echo -n '{"DYNAMIC_TOOL_DISCOVERY":"true"}' | base64)
curl -X POST "http://localhost:8080/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": { "protocolVersion": "2024-11-05", "clientInfo": {"name": "client", "version": "1.0.0"}, "capabilities": {} }
  }'

# 2) List prompts
curl -X POST "http://localhost:8080/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"prompts/list","params":{}}'

# 3) Get the capabilities prompt
curl -X POST "http://localhost:8080/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":3,"method":"prompts/get","params":{"name":"list_mcp_assets","arguments":{}}}'

Notes:

The Tools section adapts to the effective mode (Dynamic/Static/Legacy). In legacy mode, it summarizes categories instead of listing all 250+ tools.
In Static mode, toolsets shown are the authoritative list from the server’s mode enforcer (single source of truth). Session FMP_TOOL_SETS may request Static mode, but server-level configuration controls the final toolsets.
The Resources section includes a lightweight health snapshot (uptime, memory summary, version, mode).

Making HTTP Requests

The server exposes a Model Context Protocol endpoint at /mcp that accepts JSON-RPC formatted requests. Each request can include optional session configuration via query parameters.

Endpoint Format

POST http://localhost:8080/mcp[?config=BASE64_ENCODED_CONFIG]

Required Headers

Content-Type: application/json
Accept: application/json, text/event-stream
mcp-client-id: <your-client-id>

Session Management and Headers

IMPORTANT: This server uses the MCP Streamable HTTP transport, which requires session management via headers.

Required Headers for Session Persistence

| Header | When Required | Description | |--------|--------------|-------------| | mcp-client-id | All requests | Unique client identifier for session routing and caching | | mcp-session-id | After initialize | Session ID returned from initialize request | | Content-Type | All requests | Must be application/json | | Accept | All requests | Must include application/json, text/event-stream |

Critical: The mcp-client-id header is required for session persistence. Without it, each request creates an anonymous client that is NOT cached, causing "Session not found or expired" errors on subsequent requests.

Session Initialization Flow

First Request - Initialize:

# Generate a unique client ID (once per client instance)
CLIENT_ID="my-app-$(date +%s)"
   
curl -X POST "http://localhost:8080/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "mcp-client-id: $CLIENT_ID" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": {
      "protocolVersion": "2024-11-05",
      "clientInfo": {"name": "my-client", "version": "1.0.0"},
      "capabilities": {}
    }
  }'

Server Response Includes:

Header: mcp-session-id: <unique-session-id>
This session ID identifies your isolated server instance

Subsequent Requests - Include Both Session ID and Client ID:

curl -X POST "http://localhost:8080/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "mcp-client-id: $CLIENT_ID" \
  -H "mcp-session-id: <session-id-from-initialize>" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/list",
    "params": {}
  }'

Required Headers: Both mcp-client-id and mcp-session-id

Session Behavior

Isolated State: Each session has its own tool state, enabled toolsets, and configuration
Session Persistence: Sessions are maintained across requests via the mcp-session-id header
Client Caching: Clients are cached by mcp-client-id for efficient bundle reuse
Session Expiration: Sessions may expire after inactivity (handled by toolception's LRU/TTL cache)

Error Without Required Headers

If you forget to include the required headers, you'll receive:

{
  "jsonrpc": "2.0",
  "error": {
    "code": -32000,
    "message": "Session not found or expired"
  },
  "id": null
}

Solution:

Generate a unique mcp-client-id for your client instance
Include mcp-client-id in ALL requests (including initialize)
Include the returned mcp-session-id in all requests AFTER initialize

Session Configuration

Session configurations are passed as Base64-encoded JSON in the config query parameter.

Connecting to Our Hosted Instance

When connecting to our hosted instance (directly or via MCP registries), you must provide your FMP API key:

# Configuration: {"FMP_ACCESS_TOKEN":"your_fmp_api_key_here"}
CONFIG_BASE64=$(echo -n '{"FMP_ACCESS_TOKEN":"your_fmp_api_key_here"}' | base64)

# Make request to our hosted instance
curl -X POST "https://financial-modeling-prep-mcp-server-production.up.railway.app/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","clientInfo":{"name":"client","version":"1.0.0"},"capabilities":{}}}'

Note: Our hosted instance runs in dynamic mode. Static/legacy mode configurations will be ignored.

Self-Hosting Session Configuration

Session configuration only supports FMP_ACCESS_TOKEN override. Server mode and toolsets are configured at server startup only.

API Key Override (if not set server-side):

# Configuration: {"FMP_ACCESS_TOKEN":"your_key"}
CONFIG_BASE64=$(echo -n '{"FMP_ACCESS_TOKEN":"your_key"}' | base64)

Note: Mode selection (DYNAMIC_TOOL_DISCOVERY, FMP_TOOL_SETS) must be configured at server startup via environment variables or CLI arguments, not per-session.

Request Examples

1. Initialize a Dynamic Mode Session

CONFIG_BASE64=$(echo -n '{"DYNAMIC_TOOL_DISCOVERY":"true"}' | base64)
curl -X POST "http://localhost:8080/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "initialize",
    "params": {
      "protocolVersion": "2024-11-05",
      "clientInfo": {
        "name": "my-client",
        "version": "1.0.0"
      },
      "capabilities": {}
    }
  }'

Expected Response:

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "protocolVersion": "2024-11-05",
    "capabilities": {
      "tools": {
        "listChanged": true
      }
    },
    "serverInfo": {
      "name": "fmp-mcp-server",
      "version": "1.0.0"
    }
  }
}

2. List Available Tools

CONFIG_BASE64=$(echo -n '{"DYNAMIC_TOOL_DISCOVERY":"true"}' | base64)
curl -X POST "http://localhost:8080/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/list",
    "params": {}
  }'

Expected Response (Dynamic Mode):

{
  "jsonrpc": "2.0",
  "id": 2,
  "result": {
    "tools": [
      {
        "name": "enable_toolset",
        "description": "Enable a toolset by name",
        "inputSchema": {
          "type": "object",
          "properties": {
            "name": {
              "type": "string",
              "description": "Toolset name"
            }
          },
          "required": ["name"]
        }
      },
      {
        "name": "disable_toolset",
        "description": "Disable a toolset by name (state only)"
      },
      {
        "name": "list_toolsets",
        "description": "List available toolsets with active status and definitions"
      },
      {
        "name": "describe_toolset",
        "description": "Describe a toolset with definition, active status and tools"
      },
      {
        "name": "list_tools",
        "description": "List currently registered tool names (best effort)"
      }
    ]
  }
}

3. Enable a Toolset (Dynamic Mode)

CONFIG_BASE64=$(echo -n '{"DYNAMIC_TOOL_DISCOVERY":"true"}' | base64)
curl -X POST "http://localhost:8080/mcp?config=${CONFIG_BASE64}" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{
    "jsonrpc": "2.0",
    "id": 3,
    "method": "tools/call",
    "params": {
      "name": "enable_toolset",
      "arguments": {
        "toolset": "search"
      }
    }
  }'

4. Call a Financial Tool

# Requires server started with search toolset enabled (static mode) or dynamic mode
curl -X POST "http://localhost:8080/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{
    "jsonrpc": "2.0",
    "id": 4,
    "method": "tools/call",
    "params": {
      "name": "searchSymbol",
      "arguments": {
        "query": "Apple"
      }
    }
  }'

5. Get Stock Quote

# Requires server started with quotes toolset enabled (static mode) or dynamic mode
curl -X POST "http://localhost:8080/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{
    "jsonrpc": "2.0",
    "id": 5,
    "method": "tools/call",
    "params": {
      "name": "getQuote",
      "arguments": {
        "symbol": "AAPL"
      }
    }
  }'

Session and Client Behavior

Session Persistence: Sessions are cached by clientId (from mcp-client-id header)
Tool State: In dynamic mode, enabled/disabled toolsets persist for the same clientId across requests
Isolation: Sessions don't interfere with each other's tool configurations
Caching: Client storage (LRU + TTL) maintains one McpServer/DynamicToolsetManager per clientId
Session Config: Only FMP_ACCESS_TOKEN can be overridden per-session via query param

Error Handling

Common error responses:

// Invalid configuration
{
  "jsonrpc": "2.0",
  "error": {
    "code": -32000,
    "message": "Bad Request: Invalid configuration"
  },
  "id": null
}

// Tool not available
{
  "jsonrpc": "2.0",
  "error": {
    "code": -32601,
    "message": "Tool not found: toolName"
  },
  "id": 1
}

// Missing required parameters
{
  "jsonrpc": "2.0",
  "error": {
    "code": -32602,
    "message": "Missing required parameter: symbol"
  },
  "id": 2
}

Available Tools

⚠️ Important: Mode Enforcement Behavior
Server-Level Configurations Override Session Configurations:
When CLI arguments (--dynamic-tool-discovery, --fmp-tool-sets) are used, they apply to ALL sessions
When environment variables (DYNAMIC_TOOL_DISCOVERY, FMP_TOOL_SETS) are set, they apply to ALL sessions
Session-level configurations via query parameters are IGNORED when server-level modes are active
This ensures consistent behavior across all sessions on a server instance
Configuration Precedence: CLI Arguments > Environment Variables > Session Configuration
Example: If server started with --dynamic-tool-discovery, ALL sessions will use dynamic mode even if they request {"FMP_TOOL_SETS":"search,company"} in their session config.

This MCP provides the following tools for AI assistants to access financial data:

Search Tools

searchSymbol: Search for stock symbols by name or ticker
searchName: Search for companies by name
searchCIK: Search for companies by CIK number
searchCUSIP: Search for securities by CUSIP number
searchISIN: Search for securities by ISIN number
stockScreener: Screen stocks based on various criteria
searchExchangeVariants: Search for symbol variants across different exchanges
searchCompaniesByName: Search for companies by name
searchCompaniesBySymbol: Search for companies by symbol
searchCompaniesByCIK: Search for companies by CIK number

Directory and Symbol Lists

getCompanySymbols: Get a list of all company symbols
getFinancialStatementSymbols: Get a list of companies with available financial statements
getCIKList: Get a list of CIK numbers for SEC-registered entities
getSymbolChanges: Get a list of stock symbol changes
getETFList: Get a list of ETFs
getActivelyTradingList: Get a list of actively trading companies
getEarningsTranscriptList: Get a list of companies with earnings transcripts
getAvailableExchanges: Get a list of available exchanges
getAvailableSectors: Get a list of available sectors
getAvailableIndustries: Get a list of available industries
getAvailableCountries: Get a list of available countries
getAvailableTranscriptSymbols: Get a list of symbols with available transcripts
getAllIndustryClassification: Get all industry classifications
getIndustryClassificationList: Get a list of industry classifications

Financial Statements

getIncomeStatement: Get company income statements
getBalanceSheet: Get company balance sheet statements
getBalanceSheetStatement: Get company balance sheet statements
getCashFlowStatement: Get company cash flow statements
getIncomeStatementAsReported: Get income statements as reported
getBalanceSheetAsReported: Get balance sheet statements as reported
getBalanceSheetStatementAsReported: Get balance sheet statements as reported
getCashFlowStatementAsReported: Get cash flow statements as reported
getFullFinancialStatementAsReported: Get full financial statements as reported
getFinancialStatementFullAsReported: Get full financial statements as reported
getFinancialReportDates: Get dates of available financial reports
getFinancialReportsDates: Get dates of available financial reports
getLatestFinancialStatements: Get latest financial statements
getIncomeStatementTTM: Get trailing twelve months income statements
getBalanceSheetStatementTTM: Get trailing twelve months balance sheet statements
getCashFlowStatementTTM: Get trailing twelve months cash flow statements
getIncomeStatementGrowth: Get income statement growth
getBalanceSheetStatementGrowth: Get balance sheet statement growth
getCashFlowStatementGrowth: Get cash flow statement growth
getFinancialStatementGrowth: Get financial statement growth
getFinancialReportJSON: Get financial report in JSON format
getFinancialReportXLSX: Get financial report in XLSX format
getRevenueProductSegmentation: Get revenue product segmentation
getRevenueGeographicSegmentation: Get revenue geographic segmentation

Financial Metrics and Analysis

getKeyMetrics: Get key financial metrics for a company
getKeyMetricsTTM: Get key metrics for trailing twelve months
getRatios: Get financial ratios for a company
getFinancialRatios: Get financial ratios for a company
getFinancialRatiosTTM: Get financial ratios for trailing twelve months
getFinancialGrowth: Get financial growth metrics
getIncomeStatementGrowth: Get income statement growth metrics
getBalanceSheetGrowth: Get balance sheet growth metrics
getCashFlowStatementGrowth: Get cash flow statement growth metrics
getDCFValuation: Get DCF (Discounted Cash Flow) valuation for a stock
getLeveredDCFValuation: Get levered DCF valuation for a stock
calculateCustomDCF: Calculate custom DCF valuation with user-defined parameters
calculateCustomLeveredDCF: Calculate custom levered DCF valuation with user-defined parameters
getEnterpriseValue: Get enterprise value for a company
getFinancialScore: Get financial score for a company
getFinancialScores: Get financial scores for a company
getOwnerEarnings: Get owner earnings for a company

Technical Indicators

getSMA: Get Simple Moving Average (SMA) indicator
getEMA: Get Exponential Moving Average (EMA) indicator
getWMA: Get Weighted Moving Average (WMA) indicator
getDEMA: Get Double Exponential Moving Average (DEMA) indicator
getTEMA: Get Triple Exponential Moving Average (TEMA) indicator
getWilliams: Get Williams %R indicator
getADX: Get Average Directional Index (ADX) indicator
getStandardDeviation: Get Standard Deviation indicator
getRSI: Get Relative Strength Index (RSI) indicator

Quotes and Price Data

getQuote: Get current stock quote information
getBatchQuotes: Get quotes for multiple symbols
getQuoteShort: Get abbreviated stock quote information
getBatchQuotesShort: Get abbreviated quotes for multiple symbols
getHistoricalPrice: Get historical price data
getHistoricalPriceChart: Get historical price chart data
getHistoricalDailyPrice: Get historical daily price data
getHistoricalStockSplits: Get historical stock splits
getHistoricalDividends: Get historical dividends
getTechnicalIndicator: Get technical indicators for a stock
getLightChart: Get light version of price chart
getFullChart: Get full version of price chart
getUnadjustedChart: Get unadjusted price chart
getDividendAdjustedChart: Get dividend-adjusted price chart
getIntradayChart: Get intraday price chart
getAftermarketQuote: Get aftermarket quote
getAftermarketTrade: Get aftermarket trade data
getBatchAftermarketQuote: Get batch aftermarket quotes
getBatchAftermarketTrade: Get batch aftermarket trade data
getStockPriceChange: Get stock price change information

Market Indexes and Performance

getIndexList: Get a list of all market indexes
getIndexQuotes: Get quotes for market indexes
getIndexQuote: Get quote for a specific index
getIndexShortQuote: Get abbreviated quote for an index
getAllIndexQuotes: Get quotes for all market indexes
getSP500Constituents: Get S&P 500 constituent companies
getHistoricalSP500Changes: Get historical S&P 500 changes
getNasdaqConstituents: Get NASDAQ constituent companies
getDowJonesConstituents: Get Dow Jones constituent companies
getHistoricalNasdaqChanges: Get historical NASDAQ changes
getHistoricalDowJonesChanges: Get historical Dow Jones changes
getSectorPerformance: Get sector performance data
getHistoricalSectorPerformance: Get historical sector performance
getBiggestGainers: Get biggest gaining stocks
getBiggestLosers: Get biggest losing stocks
getMostActiveStocks: Get most active stocks
getHistoricalIndexFullChart: Get historical index full chart
getHistoricalIndexLightChart: Get historical index light chart
getIndex1MinuteData: Get 1-minute index data
getIndex5MinuteData: Get 5-minute index data
getIndex1HourData: Get 1-hour index data
getSectorPerformanceSnapshot: Get sector performance snapshot
getSectorPESnapshot: Get sector PE ratio snapshot
getIndustryPerformanceSnapshot: Get industry performance snapshot
getIndustryPerformanceSummary: Get industry performance summary
getIndustryPESnapshot: Get industry PE ratio snapshot
getHistoricalIndustryPerformance: Get historical industry performance
getHistoricalIndustryPE: Get historical industry PE ratios
getHistoricalSectorPE: Get historical sector PE ratios

Market Data

getMarketHours: Get market hours for a specific exchange
getExchangeMarketHours: Get market hours for a specific exchange
getHolidaysByExchange: Get holidays for a specific exchange with optional date range filtering
getAllExchangeMarketHours: Get market hours for all exchanges
getEarningsCalendar: Get earnings announcement calendar
getIPOCalendar: Get initial public offering calendar
getStockSplitCalendar: Get stock split calendar
getDividendCalendar: Get dividend calendar
getEconomicCalendar: Get economic events calendar
getIPODisclosures: Get IPO disclosures
getIPOProspectuses: Get IPO prospectuses

News and Press Releases

getFMPArticles: Get financial news articles from FMP
getGeneralNews: Get general financial news
getStockNews: Get news for specific stocks
getStockNewsSentiment: Get news with sentiment analysis
getPressReleases: Get company press releases
searchStockNews: Search stock news
searchPressReleases: Search press releases
getCryptoNews: Get cryptocurrency news
searchCryptoNews: Search cryptocurrency news
getForexNews: Get forex news
searchForexNews: Search forex news

SEC Filings

getLatestFinancialFilings: Get latest financial filings
getFilingsBySymbol: Get filings by symbol
getFilingsByCIK: Get filings by CIK
getFilingsByFormType: Get filings by form type
getLatest8KFilings: Get latest 8-K filings
getSecFilingExtract: Get SEC filing extract
getFilingExtractAnalyticsByHolder: Get filing extract analytics by holder

Insider and Institutional Trading

getInsiderTrading: Get insider trading data
getInsiderRoster: Get insider roster for a company
getInsiderRosterStatistics: Get statistics on insider roster
getInsiderTransactionTypes: Get types of insider transactions
getInsiderOwnership: Get insider ownership information
getInstitutionalOwnership: Get institutional ownership data
getInstitutionalHolders: Get institutional holders for a company
getInstitutionalHoldersList: Get list of institutional holders
getInstitutionalHolderPortfolioDates: Get portfolio dates for institutional holders
get13FFilings: Get 13F filings
get13FDates: Get dates of 13F filings
getForm13FFilingDates: Get 13F filing dates
getLatestInsiderTrading: Get latest insider trading data
searchInsiderTrades: Search insider trades
searchInsiderTradesByReportingName: Search insider trades by reporting name
getInsiderTradeStatistics: Get insider trade statistics
getLatestInstitutionalFilings: Get latest institutional filings
getHolderPerformanceSummary: Get holder performance summary
getHolderIndustryBreakdown: Get holder industry breakdown
getPositionsSummary: Get positions summary

ETFs and Funds

getETFHolder: Get ETF holder information
getETFSectorWeighting: Get ETF sector weightings
getETFCountryWeighting: Get ETF country weightings
getETFExposure: Get ETF exposure to stocks
getFundInfo: Get fund information
getFundHolder: Get fund holder information
getFundSectorWeighting: Get fund sector weightings
getFundHoldings: Get fund holdings
getFundCountryAllocation: Get fund country allocation
getFundAssetExposure: Get fund asset exposure
getDisclosure: Get latest fund disclosure holders information
getFundDisclosure: Get comprehensive fund disclosure data by year/quarter
searchFundDisclosures: Search fund disclosures by holder name
getFundDisclosureDates: Get fund disclosure dates (with optional CIK)
getETFHoldersBulk: Get ETF holders in bulk
getETFQuotes: Get ETF quotes
getMutualFundQuotes: Get mutual fund quotes

Government Trading

getGovernmentTradingList: Get government trading list
getSenateTrading: Get senate trading data
getHouseTrading: Get house trading data
getSenateTrades: Get senate trades
getSenateTradesByName: Get senate trades by name
getHouseTrades: Get house trades
getHouseTradesByName: Get house trades by name
getLatestSenateDisclosures: Get latest senate disclosures
getLatestHouseDisclosures: Get latest house disclosures

Cryptocurrency and Forex

getCryptocurrencyList: Get a list of cryptocurrencies
getCryptocurrencyQuote: Get cryptocurrency quote
**getCry

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

Financial Modeling Prep MCP (Model Context Protocol) Server

Table of Contents

Quick Start

🚀 Option 1: Use Our Hosted Instance (Fastest)

🏠 Option 2: Self-Host Your Own Instance (Full Control)

Features

Deployment Options

📡 Using Our Hosted Instance (Recommended for Quick Start)

🏠 Self-Hosting Your Own Instance (Full Control)

Server Architecture

Key Features:

Transport & Client Compatibility

Request Flow:

Available HTTP Endpoints:

Configuration & Mode Enforcement

Understanding Server Modes

Using Our Hosted Instance (Railway)

Self-Hosting Your Own Instance

Available Modes

1. 🔀 Dynamic Mode (DYNAMIC_TOOL_DISCOVERY=true)

2. 🔧 Static Mode (FMP_TOOL_SETS=search,company,quotes)

3. 📚 Legacy Mode (no specific configuration)

Configuration Precedence (Self-Hosted Only)

⚠️ Important Mode Enforcement Behavior (Self-Hosted)

Configuration Methods:

⚠️ Configuration Warnings

Selective Tool Loading

Available Tool Sets

Dynamic Toolset Management (BETA)

How It Works

Configuration Options

Server-Level Configuration (Affects All Sessions)

Session-Level Configuration (When No Server Override)

Example Workflow

Benefits

Usage

Registries

MCP Registry

Quick Start from Registry

Registry Installation Methods

Quick Start Guide for Registry Users

AI Platform Integration

Installation Methods

NPM Installation

Docker Installation

Source Installation

Environment Variables

Verification

Troubleshooting

Smithery.ai

Important Update: Smithery Hosting Changes (March 2026)

Using Our Hosted Instance

Getting Your FMP API Key

Want Different Configuration?

Glama.ai

Contexaai.com

HTTP Server & Local Development

Basic Server Setup

Server-Level Mode Configuration

Custom Port Configuration

Example System Prompts

For Dynamic Toolset Mode

For Static Toolset Mode

Usage Tips

Human-Friendly Capabilities Prompt

List assets via prompts

Making HTTP Requests

Endpoint Format

Required Headers

Session Management and Headers

Required Headers for Session Persistence

Session Initialization Flow

Session Behavior

Error Without Required Headers

1. 🔀 Dynamic Mode (`DYNAMIC_TOOL_DISCOVERY=true`)

2. 🔧 Static Mode (`FMP_TOOL_SETS=search,company,quotes`)