npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@iwy/mcp

v0.4.0

Published

Model Context Protocol (MCP) server for iwy.ai API integration - enables Claude to manage AI agents and tools

Readme

iwy.ai MCP Server

npm version License: MIT

⚠️ *Beta Pre-Release - This is an early version. API may change.

Model Context Protocol (MCP) server for iwy.ai - enables Claude to create and manage AI agents and tool integrations through the iwy.ai API.

Features

  • Complete Agent Management: Create, read, update, and delete AI conversational agents
  • Tool Integration: Manage webhook-based tools for agent capabilities
  • Testing Support: Test tools before deploying to production agents
  • Comprehensive Documentation: Built-in API reference and configuration guides
  • Type Safety: Full TypeScript support with Zod validation
  • Robust Error Handling: Automatic retries and detailed error messages

Installation

Global Installation (Recommended)

npm install -g @iwy/mcp

Local Installation

npm install @iwy/mcp

Configuration

1. Get Your API Key

  1. Visit app.iwy.ai/settings
  2. Generate a new API key
  3. Save it securely

2. Configure Claude

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "iwy": {
      "command": "npx",
      "args": ["-y", "@iwy/mcp"],
      "env": {
        "IWY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Claude Code

Installation Steps:

  1. Install the package globally:
npm install -g @iwy/mcp
  1. Use jq to add the server to ~/.claude.json:
jq '.mcpServers["iwy"] = {
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "@iwy/mcp"],
  "env": {
    "IWY_API_KEY": "your_api_key_here"
  }
}' ~/.claude.json > ~/.claude.json.tmp && mv ~/.claude.json.tmp ~/.claude.json

Or manually edit ~/.claude.json and add to the mcpServers object:

{
  "mcpServers": {
    "iwy": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@iwy/mcp"],
      "env": {
        "IWY_API_KEY": "your_api_key_here"
      }
    }
  }
}
  1. Restart Claude Code to load the MCP server.

Testing:

# List your agents
"List my iwy.ai agents"

# Get agent details
"Show me details for agent <agent_id>"

# Create a new agent
"Create an iwy.ai customer service agent"

3. Environment Variable

Alternatively, set the API key as an environment variable:

export IWY_API_KEY="your_api_key_here"

Known Issues

API Endpoint Version (Current Package)

The current npm package version may use the wrong API endpoint (https://api.iwy.ai instead of https://api.iwy.ai/v1). This has been identified and will be fixed in the next release.

Temporary Workaround (if you encounter "Resource not found" errors):

Find your global npm packages location and update the API client:

# Find the installation path
NPM_PATH=$(npm root -g)/@iwy/mcp/dist/client.js

# Update the baseURL
sed -i "s|baseURL: 'https://api.iwy.ai'|baseURL: 'https://api.iwy.ai/v1'|" "$NPM_PATH"

This will be resolved in version 0.2.2+.

Available Tools

Agent Management (5 tools)

| Tool | Description | |------|-------------| | list_iwy_agents | List all agents in your account | | get_iwy_agent | Get detailed agent configuration | | create_iwy_agent | Create a new AI agent | | update_iwy_agent | Update existing agent | | delete_iwy_agent | Delete an agent |

Tool Management (6 tools)

| Tool | Description | |------|-------------| | list_iwy_tools | List all webhook tools | | get_iwy_tool | Get detailed tool configuration | | create_iwy_tool | Create a new tool integration | | update_iwy_tool | Update existing tool | | delete_iwy_tool | Delete a tool | | test_iwy_tool | Test tool execution |

Usage Examples

Creating a Customer Service Agent

User: Create a customer service agent for my e-commerce store

Claude: I'll create an iwy.ai agent for customer service.

[Creates agent with appropriate configuration]

✅ Created agent with ID: 550e8400-e29b-41d4-a716-446655440000

Adding a Weather Tool

User: Add a weather lookup tool

Claude: I'll create a tool integration for weather lookup.

[Creates tool with webhook configuration]

✅ Created tool with ID: dcfae097-1b37-4444-bb0c-1a6abb0320fd

Testing a Tool

User: Test the weather tool with "San Francisco"

Claude: [Tests tool with parameters]

✅ Test successful!
- Execution time: 245ms
- Response: {"temperature": 68, "conditions": "sunny"}

Documentation Resources

The server provides three built-in documentation resources accessible through Claude:

  • iwy://docs/agents - Agent API reference
  • iwy://docs/tools - Tool API reference
  • iwy://docs/configuration - Setup and configuration guide

Development

Building from Source

git clone https://github.com/iwy-ai/mcp.git
cd mcp
npm install
npm run build

Running Locally

export IWY_API_KEY="your_api_key_here"
node dist/index.js

Architecture

src/
├── index.ts              # MCP server entry point
├── client.ts             # iwy.ai API client
├── types.ts              # TypeScript type definitions
├── schemas/
│   ├── agent.ts          # Agent validation schemas
│   └── tool.ts           # Tool validation schemas
├── tools/
│   ├── agents.ts         # Agent tool handlers
│   └── tools.ts          # Tool tool handlers
├── utils/
│   ├── errors.ts         # Error handling
│   └── validation.ts     # Input validation
└── resources/
    ├── agent-docs.md     # Agent documentation
    ├── tool-docs.md      # Tool documentation
    └── config-guide.md   # Configuration guide

Error Handling

The server provides detailed error messages with suggestions:

| Error Code | Description | Suggestion | |------------|-------------|------------| | UNAUTHORIZED | Invalid API key | Check IWY_API_KEY configuration | | NOT_FOUND | Resource doesn't exist | Use list operation to find valid IDs | | INVALID_REQUEST | Validation failed | Check required fields and types | | SERVER_ERROR | iwy.ai API error | Automatic retry, contact support if persists | | TIMEOUT | Request timeout | Increase timeout or retry |

Requirements

License

MIT License - see LICENSE file for details

Links

Support

For issues, questions, or feature requests:

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request