RASON MCP Server

AI-powered platform for decision intelligence: building, analyzing, and solving optimization, simulation, data science, and decision models with RASON.

Using VS Code? Check out RASON Desktop, Frontline's flagship VS Code extension. It bundles this MCP server; a RASON language server (IntelliSense, validation, signature help); built-in local & cloud solvers; model and examples sidebars; live Power BI / Excel integration with auto-refreshing charts; one-click result export; and more.

RASON MCP Server in Claude Desktop — solving a product mix optimization model with results table, constraint utilization chart, and key insights.

🔍 Click the screenshot to view full size.

Works across all major RASON model types

Click any model type to see it in action.

What is RASON?

RASON (Restful Analytic Solver® Object Notation) is a multi-purpose modeling language and decision intelligence platform by Frontline Systems for building, analyzing, and solving mathematical optimization, simulation / risk analysis, and data science / machine learning models, plus business decision rules and multi-stage decision flows.

You can use RASON models on your desktop with RASON Desktop for VS Code, Power BI Desktop and Excel Desktop; in the Azure cloud with a REST API working with Microsoft Fabric, Power BI Service and Excel for the Web; in Docker containers; and in your own app written in C/C++, C#, Java, Python, and R via Frontline's Solver SDK.

RASON comes with world-class solvers for mathematical optimization, advanced probability distributions and simulation, powerful machine learning algorithms, rich DMN business rule handling, and easy-to-build multi-stage decision flows with an in-memory SQL engine.

About This MCP Server

This MCP server is more than a REST API wrapper — it's a complete AI infrastructure for analytical modeling. It includes a searchable library of nearly 200 example models, templates that guide model generation, structural analysis, and solve result interpretation. An AI assistant connected to this server can help formulate a model from a business problem description, find relevant examples, explain model structure, submit it for solving, and present results in a goal-oriented way — closing the loop with suggested next steps and improvements.

What Can You Do With It?

Explore nearly 200 ready-made examples

"Find examples of portfolio optimization"

"Show me a vehicle routing model I can start from"

"What simulation examples are available?"

Build models from templates

"Create a new linear optimization model"

"Give me a decision table template"

"Start a simulation model from scratch"

Analyze and understand models

"Describe the structure of this model — what type is it?"

"What variables and constraints does this optimization model have?"

"Explain what this model is doing"

Solve optimization, simulation, data science & decision models

"Solve this product mix model and show me the optimal allocation"

"Run a Monte Carlo simulation on this risk model"

"Evaluate this decision table with the following inputs"

"Train a classification model to predict customer churn"

Go beyond simple commands

"I have a scheduling problem with 8 employees and shift constraints — build me an optimization model, solve it, and show the schedule as a table"

"Find a portfolio optimization example, adapt it for 3 assets with a 15% risk budget, solve it, and summarize the allocation"

"Submit my model for solve, keep polling status, and when it's done show results in a table with key insights"

"This model is infeasible — run diagnostics and suggest which constraints to relax"

Manage models in your RASON account

"List all my optimization models"

"Upload this RASON model with its CSV data files"

"Create a new version of 'supply-chain' and set it as the champion"

"Clean up all old versions of 'product-mix' — keep only the champion"

Getting Started

Three ways to install.

1. Claude Desktop: drop-in extension

Grab the latest MCPB release, then in Claude Desktop open Settings → Extensions → Advanced Settings → Install Extension and pick the file. On macOS you can also drag the .mcpb onto the app window. The install dialog offers to set a RASON bearer token — only needed to solve models or manage them in the cloud, and can be set later from the extension's settings.

2. npm: any MCP client

For Claude Desktop, Cursor, Windsurf, Claude Code, or any other stdio MCP client, add this entry to your client's MCP config.

{
  "mcpServers": {
    "rason": {
      "command": "npx",
      "args": ["-y", "@frontlinesystems/rason-mcp-server"],
      "env": {
        "RASON_BEARER_TOKEN": "your_token_here"
      }
    }
  }
}

Omit env or RASON_BEARER_TOKEN to use the no-account tools only.

Add the config above to your config file:

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

See Claude Desktop MCP setup for details.

Create or update an MCP configuration file such as .vscode/mcp.json in your workspace or the user-level MCP config, using VS Code's "servers" shape:

{
  "servers": {
    "rason": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@frontlinesystems/rason-mcp-server"],
      "env": {
        "RASON_BEARER_TOKEN": "your_token_here"
      }
    }
  }
}

See VS Code MCP setup for details.

claude mcp add --transport stdio --env RASON_BEARER_TOKEN=your_token_here rason -- npx -y @frontlinesystems/rason-mcp-server

You can omit --env RASON_BEARER_TOKEN=... to use only the no-account tools.

See Claude Code MCP setup for details.

Add the config above under "mcpServers" in .cursor/mcp.json (project) or ~/.cursor/mcp.json (global).

See Cursor MCP setup for details.

Add the config above under "mcpServers" in ~/.codeium/windsurf/mcp_config.json.

See Windsurf MCP setup for details.

This server works with any MCP-compatible client over stdio. Configure it with:

• Command: npx
• Arguments: -y @frontlinesystems/rason-mcp-server
• Transport: stdio
• Environment variables: See Configuration below

3. VS Code: one-click extension

Two extensions are available on the Marketplace:

• RASON MCP Server: this MCP server, standalone.
• RASON Desktop: Frontline's flagship VS Code extension. Bundles this MCP server; a RASON language server (IntelliSense, validation, signature help); built-in local & cloud solvers; model and examples sidebars; live Power BI / Excel integration with auto-refreshing charts; one-click result export; and more.

Set the auth token in either extension via the Command Palette: RASON: Set Auth Token.

Works Without a RASON Account

Example search, model templates, model analysis, and RASON info tools work without credentials. You can explore the full example library and build models before signing up. A RASON account is needed only for solving models and managing models in the cloud.

Configuration

Set these environment variables in your MCP client config (see Getting Started above):

| Variable | Default | Description | |----------|---------|-------------| | RASON_BEARER_TOKEN | — | Auth token from your RASON account. Required for solving and model management. | | RASON_SERVER_URL | https://rason.net | RASON server URL. | | RASON_RESULT_ARRAY_LIMIT | 25 | Max array/dataFrame rows before summarizing | | RASON_RESULT_SIZE_LIMIT | 50000 | Max result characters before truncating | | RASON_REQUEST_TIMEOUT | 300000 | Request timeout in ms (default: 5 minutes) |

Tools

Examples & Templates

• search_examples: Search ~200 example models by keyword or type (optimization, simulation, datamining/data science, calculation/decision tables, flow/multi-stage pipelines)
• get_example: Retrieve a specific example model with full definition and metadata
• get_model_template: Get a bare JSON scaffold for a model type: blank, optimization, simulation, sim-optimization, data-science, workflow, decision-table, power-bi

Analysis

• describe_model: Analyze model structure: type/subtype detection, component inventory, issue identification
• about_rason: RASON capabilities, model types, Frontline Systems ecosystem, and server info

Solving

• solve_model: Solve a model synchronously (inline RASON, RASON files, or Excel workbooks)
• submit_solve: Submit a model for asynchronous solving (long-running models)
• get_solve_status: Check solving status and progress
• get_solve_result: Retrieve the result once solving is complete
• stop_solve: Stop a running solve (intermediate results may be available)

Diagnostics

• diagnose_model: Run diagnostics synchronously (useful for infeasible/unbounded optimization models)
• submit_diagnose: Submit for asynchronous diagnostics

Model Management

• list_models: List models in your account with optional filters by type and kind
• get_model: Retrieve a model definition (RASON JSON)
• post_model: Create a new model from a RASON JSON definition
• post_model_with_files: Upload a model with file attachments (RASON + data files, or Excel)
• put_model: Update an existing model or create a new version
• put_model_with_files: Update a model with file attachments
• set_champion: Set or unset the champion (default) version of a model
• delete_model: Delete models with flexible filtering by kind, type, and force option

Prompts & Resources

The server includes 12 guided prompts for common workflows (solving, uploading, diagnostics, model management) and 2 resources — a live model catalog and a browsable example library reference.

Disclaimer

This software is provided "as is", without warranty of any kind. Use of this MCP server involves interaction with external cloud services (RASON REST API). You are responsible for reviewing actions before they are executed, managing your own credentials securely, and ensuring compliance with applicable terms of service. Before uploading models, files, or data to RASON cloud services, review Frontline Systems' Terms and Conditions and Privacy Policy. AI-generated model formulations and interpretations of solve results should be validated before use in production or decision-making.

License

Copyright © 2026 Frontline Systems, Inc. All rights reserved. This is proprietary software; no part may be reproduced, distributed, or modified without prior written permission from Frontline Systems. Use is governed by the Frontline Systems Software License. For licensing inquiries, contact Frontline Systems.

Feedback and Support

This software is developed and maintained by Frontline Systems, Inc. For questions, feedback, or licensing inquiries, please contact your Frontline representative or reach us at solver.com/how-may-we-help-you.

Links

• RASON Portal: create a free account, manage models, documentation
• Frontline Systems: the company behind RASON and Analytic Solver
• MCP Protocol: learn about the Model Context Protocol