mcpField
A
AI SDK MCP Docs Server

AI SDK MCP Docs Server

Local
github.com/mongolyyMemory & Knowledge1Updated 80w ago
Repository

About AI SDK MCP Docs Server

An unofficial MCP server that makes AI SDK documentation, cookbook examples, and provider details available to IDEs and other MCP clients. It retrieves and parses content from the AI SDK website.

Key features

  1. 01Retrieve AI SDK documentation
  2. 02Browse cookbook examples and tutorials
  3. 03Look up provider information
  4. 04Fetch all entries or a specific path

Use cases

  1. 01Find documentation while working in an IDE
  2. 02Retrieve a specific cookbook example
  3. 03Check details for an AI SDK provider

MCP support

Exposes documentation, cookbook, and provider lookup tools through MCP. Clients can request lists or fetch content by path.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "ai-sdk-mcp-docs-server": {
      "command": "npx",
      "args": [
        "-y",
        "fastmcp"
      ]
    }
  }
}
Run commandnpx -y fastmcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmfastmcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

AI SDK MCP Docs Server

A Model Context Protocol (MCP) server that provides AI SDK documentation, cookbook examples, and provider information.

Note

This is an unofficial tool and does not provide any guarantees regarding functionality or accuracy.

Features

  • Access AI SDK documentation content
  • Retrieve cookbook examples and tutorials
  • Get information about AI providers

Setting up with IDE

This tool can be used with various IDEs that support MCP servers.

Common Setup

  1. Clone the repository to your local machine:

    git clone https://github.com/mongolyy/ai-sdk-mcp-docs-server.git
cd ai-sdk-mcp-docs-server

  2. Install dependencies:

    npm install
IDE-Specific Configuration
Cline

  1. Open Cline

  2. Click MCP Servers link icon

  3. Navigate to Installed tab and click configure MCP Servers button

  4. Add a new MCP server with the following configuration (update the path to match your local repository location):

    {
  "mcpServers": {
+    "ai-sdk-mcp-docs-server": {
+      "command": "npx",
+      "args": [
+        "tsx",
+        "/Users/username/path/to/ai-sdk-mcp-docs-server/src/index.ts"
+      ]
+    }
  }
}

  5. Save the settings

  6. Restart Cline to apply the changes

Cursor

  1. Edit the ~/.cursor/mcp.json file

  2. Add or update the MCP server configuration (update the path to match your local repository location):

    {
  "mcpServers": {
+    "ai-sdk-mcp-docs-server": {
+      "command": "npx",
+      "args": [
+        "tsx",
+        "/Users/username/path/to/ai-sdk-mcp-docs-server/src/index.ts"
+      ]
+    }
  }
}

  3. Save the file

  4. Restart Cursor to apply the changes

Development

This section provides guidelines for contributing to the project, including coding standards, testing procedures, and how to submit pull requests.

Installation
npm install
Run on local

CLI:

npx fastmcp dev src/index.ts

GUI:

npx fastmcp inspect src/index.ts

Available Tools

  • docs - Get AI SDK documentation

    • Without path: Get list of all docs
    • With path: /docs/introduction - Get specific doc

  • cookbook - Get cookbook examples

    • Without path: Get list of all examples
    • With path: /cookbook/next/generate-text - Get specific example

  • providers - Get provider information

    • Without path: Get list of all providers
    • With path: /providers/ai-sdk-providers - Get specific provider info

How It Works

The server fetches content from the AI SDK website, parses the HTML, and provides the content through a structured API accessible via the Model Context Protocol.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.