Skip to main content
Glama

Inngest MCP Docs Server

by inngest

Inngest MCP Docs Server

A Model Context Protocol (MCP) server that provides access to Inngest documentation by fetching and converting web content to Markdown format. This server enables AI coding agents to access up-to-date Inngest documentation directly within supported tools like Cursor and Claude Code.

Features

  • 🔄 Real-time Documentation Access: Fetches the latest Inngest documentation from the web
  • 📝 Markdown Conversion: Converts HTML documentation to clean, readable Markdown
  • 🚀 Easy Integration: Simple setup with Cursor and Claude Code
  • 🛠️ Extensible: Built with TypeScript and easily customizable

Installation

Prerequisites

  • Node.js 18 or higher
  • npm/pnpm/yarn package manager
  • Cursor or Claude Code installed

Clone & Install

  1. Clone this repository:
    git clone https://github.com/your-username/inngest-mcp.git cd inngest-mcp
  2. Install dependencies:
    npm install
  3. Choose your installation method below based on your preferred tool.

Cursor Setup

Option A: One-Click Install (Easiest)

Use the install button below 👇

Option B: Manual Configuration
  1. Open Cursor Settings:
    • Go to CursorCursor Settings
    • Navigate to the MCP section in the GUI
  2. Add the MCP server configuration:
    { "inngest-docs-server": { "command": "npx", "args": ["-y", "tsx", "/path/to/your/inngest-mcp/index.ts"], "enabled": true } }
  3. Update the path:
    • Replace /path/to/your/inngest-mcp/index.ts with the actual path to your index.ts file
  4. Restart Cursor to apply the changes

Claude Code Setup

# Navigate to your project directory cd /path/to/your/inngest-mcp # Add the MCP server claude mcp add inngest-docs-server npx -y tsx ./index.ts
Option B: Scope-Specific Installation

Local Scope (Project-specific):

claude mcp add inngest-docs-server -s local npx -y tsx ./index.ts

Project Scope (Team-shared):

claude mcp add inngest-docs-server -s project npx -y tsx ./index.ts

User Scope (Global):

claude mcp add inngest-docs-server -s user npx -y tsx ./index.ts
Option C: JSON Configuration

Create or update your .mcp.json file:

{ "mcpServers": { "inngest-docs-server": { "command": "npx", "args": ["-y", "tsx", "/path/to/your/inngest-mcp/index.ts"], "env": {} } } }

Usage

Once installed, you can use the Inngest MCP server in your AI assistant:

Available Tools

  • fetch_docs: Fetches and converts Inngest documentation to Markdown

Example Prompts

"Can you fetch the latest Inngest documentation about steps and workflows?" "Use the fetch_docs tool to get information about Inngest functions" "Help me understand Inngest workflows by fetching the documentation"

In Cursor

  1. Open any file in your project
  2. Use the AI chat feature
  3. Ask questions about Inngest documentation
  4. The AI will automatically use the MCP server to fetch current documentation

In Claude Code

  1. Start a conversation with Claude
  2. Use the /mcp command to check server status
  3. Ask questions about Inngest, and Claude will fetch the latest documentation

Development

Project Structure

inngest-mcp/ ├── index.ts # Main MCP server implementation ├── package.json # Dependencies and scripts ├── package-lock.json # Lock file └── README.md # This file

Contributing

The server is built with TypeScript and uses:

  • @modelcontextprotocol/sdk: MCP protocol implementation
  • cheerio: HTML parsing and manipulation
  • turndown: HTML to Markdown conversion

We welcome contributions! You can help by adding new tools to expose more of the Inngest documentation to AI assistants. This creates a powerful workflow for developers, allowing AI assistants to have a more native understanding of Inngest when helping you build.

How to Add a New Tool

To add a new tool, you'll need to register it with the MCP server in index.ts. This allows AI assistants like Cursor and Claude Code to discover and use your new tool.

Here is an example of how to add a new tool that fetches documentation about Inngest:

  1. Open index.ts and find the server.registerTool section.
  2. Add a new tool definition. Use the server.registerTool method.
    • Choose a specific and descriptive name for your tool (e.g., fetch_events_docs).
    • Write a clear title and description so that the AI knows what the tool does.
    • Call fetchDocuments with the relevant URLs.
    // in index.ts // ... existing fetch_docs tool ... server.registerTool( "fetch_events_docs", // A specific, descriptive name { title: "Fetch Inngest Events Documentation", description: "Fetches and converts documentation about Inngest Events, including how to send and receive them.", }, async () => { const text = await fetchDocuments([ "https://www.inngest.com/docs/getting-started/send-and-receive-events", "https://www.inngest.com/docs/reference/event-payload", // Add more relevant URLs here ]); return { content: [{ type: "text", text }], }; } );
Contribution Workflow

To contribute your changes:

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/new-docs-tool
  3. Add your new tool to index.ts.
  4. Test your changes.
  5. Submit a pull request.

Troubleshooting

Common Issues

"Command not found" errors:

  • Ensure Node.js and npm are installed
  • Verify the path to your index.ts file is correct
  • Try using absolute paths instead of relative paths

"Permission denied" errors:

  • Check file permissions: chmod +x index.ts
  • Ensure you have read/write access to the project directory

Server not connecting:

  • Verify the MCP server is properly configured
  • Check that all dependencies are installed
  • Restart your IDE after configuration changes

Claude Code Specific

Check server status:

claude mcp list claude mcp get inngest-docs-server

Remove and re-add server:

claude mcp remove inngest-docs-server claude mcp add inngest-docs-server npx -y tsx ./index.ts

Reset project choices:

claude mcp reset-project-choices

Cursor Specific

Verify configuration:

  1. Go to Cursor Settings → MCP
  2. Check that the server is listed and enabled
  3. Verify the command path is correct

Restart Cursor:

  • Close Cursor completely
  • Reopen and try again

Debug Mode

Enable debug logging by setting environment variables:

# For development DEBUG=mcp:* npx tsx index.ts # For Claude Code claude mcp add inngest-docs-server -e DEBUG=mcp:* npx -y tsx ./index.ts
-
security - not tested
F
license - not found
-
quality - not tested

A Model Context Protocol server that provides AI coding agents with access to up-to-date Inngest documentation by fetching and converting web content to Markdown format.

  1. Features
    1. Installation
      1. Prerequisites
      2. Clone & Install
      3. Cursor Setup
      4. Claude Code Setup
    2. Usage
      1. Available Tools
      2. Example Prompts
      3. In Cursor
      4. In Claude Code
    3. Development
      1. Project Structure
      2. Contributing
    4. Troubleshooting
      1. Common Issues
      2. Claude Code Specific
      3. Cursor Specific
      4. Debug Mode

    Related MCP Servers

    • A
      security
      A
      license
      A
      quality
      A Model Context Protocol server that enables AI agents to retrieve and understand entire codebases at once, providing tools to analyze local workspaces or remote GitHub repositories.
      Last updated -
      3
      44
      TypeScript
      MIT License
      • Linux
      • Apple
    • -
      security
      A
      license
      -
      quality
      A Model Context Protocol server that enhances AI agents by providing deep semantic understanding of codebases, enabling more intelligent interactions through advanced code search and contextual awareness.
      Last updated -
      48
      Python
      MIT License
      • Apple
    • -
      security
      F
      license
      -
      quality
      A Model Context Protocol server that provides AI models with structured access to external data and services, acting as a bridge between AI assistants and applications, databases, and APIs in a standardized, secure way.
      Last updated -
      1
      Python
    • A
      security
      F
      license
      A
      quality
      A Model Context Protocol server that intelligently fetches and processes web content, transforming websites and documentation into clean, structured markdown with nested URL crawling capabilities.
      Last updated -
      2
      552
      1
      TypeScript

    View all related MCP servers

    MCP directory API

    We provide all the information about MCP servers via our MCP API.

    curl -X GET 'https://glama.ai/api/mcp/v1/servers/inngest/docs-mcp'

    If you have feedback or need assistance with the MCP directory API, please join our Discord server