APIWeaver

v1.0.0โ€ขAPIsโ€ขstable

A FastMCP server that dynamically creates MCP (Model Context Protocol) servers from web API configurations. This allows you to easily integrate any REST API, GraphQL endpoint, or web service into an MCP-compatible tool that can be used by AI assistan

apiweavermcpai-integration
Share:
50
Stars
0
Downloads
0
Weekly
0/5

What is APIWeaver?

APIWeaver is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to fastmcp server that dynamically creates mcp (model context protocol) servers from web api configurations. this allows you to easily integrate any rest api, graphql endpoint, or web service into an mcp...

A FastMCP server that dynamically creates MCP (Model Context Protocol) servers from web API configurations. This allows you to easily integrate any REST API, GraphQL endpoint, or web service into an MCP-compatible tool that can be used by AI assistan

This server falls under the APIs and Developer Tools categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A FastMCP server that dynamically creates MCP (Model Context

Use Cases

Create MCP servers dynamically from any REST API or GraphQL endpoint.
Integrate web services into AI-compatible tools automatically.
GongRzhe

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedApr 27, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx apiweaver

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use APIWeaver

APIWeaver is a FastMCP-based Python server that dynamically creates MCP tools from web API configurations, allowing you to integrate any REST API, GraphQL endpoint, or web service into an MCP-compatible tool without writing custom server code. You describe your API once using a configuration format that specifies the base URL, authentication method, headers, and endpoint definitions, and APIWeaver instantly makes those endpoints callable by AI assistants. Developers use it to rapidly connect Claude or other AI clients to internal APIs, third-party services, or prototyping APIs without building a dedicated MCP server for each one.

Prerequisites

  • Python 3.8 or higher with pip installed
  • The APIWeaver repository cloned locally
  • API credentials or tokens for any external services you want to integrate
  • An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
1

Clone the APIWeaver repository

Clone the repository from GitHub and enter the project directory.

git clone https://github.com/GongRzhe/APIWeaver.git
cd APIWeaver
2

Install dependencies

Install the required Python packages. APIWeaver uses FastMCP and httpx for making API calls.

pip install -r requirements.txt
# or install as a package:
pip install .
3

Configure your MCP client

Add the APIWeaver server to your MCP client configuration. It runs via Python and uses stdio transport.

4

Register your first API

Ask your AI assistant to call the register_api tool with the name, base_url, description, authentication details, and endpoint definitions for the API you want to integrate. APIWeaver will create callable tools for each endpoint.

5

Test connectivity and call endpoints

Use the test_api_connection tool to verify APIWeaver can reach your API, then use call_api or the auto-generated endpoint tools to make real requests.

6

List and manage registered APIs

Use list_apis to see all registered APIs and their endpoints. Use unregister_api to remove integrations that are no longer needed.

APIWeaver Examples

Client configuration

Example claude_desktop_config.json entry to launch the APIWeaver Python server. Adjust the path to match where you cloned the repository.

{
  "mcpServers": {
    "apiweaver": {
      "command": "python",
      "args": ["/absolute/path/to/APIWeaver/main.py"]
    }
  }
}

Prompts to try

Example prompts that exercise the six built-in APIWeaver tools for registering and calling web APIs.

- "Register the JSONPlaceholder API with base URL https://jsonplaceholder.typicode.com and add a GET /posts endpoint"
- "List all APIs currently registered in APIWeaver"
- "Test the connection to the JSONPlaceholder API"
- "Call the GET /posts endpoint on JSONPlaceholder and return the first 5 results"
- "Get the API schema for the JSONPlaceholder integration"
- "Register our internal inventory API at http://internal.api/v2 with Bearer token auth and add GET /products and POST /orders endpoints"

Troubleshooting APIWeaver

ModuleNotFoundError when starting the server

Run 'pip install -r requirements.txt' from the APIWeaver directory. If you have multiple Python versions, ensure you are installing into the same Python environment that your MCP client will use to launch the server.

register_api succeeds but API calls return authentication errors

Verify the auth configuration passed to register_api matches what your target API expects (Bearer token, API key header, Basic auth, etc.). Use get_api_schema to inspect the registered configuration and correct any mismatches.

call_api returns a connection timeout

Use test_api_connection to check basic reachability. If the API is internal, ensure the machine running the APIWeaver server can reach the internal network. For HTTPS APIs, confirm that SSL certificates are valid.

Frequently Asked Questions about APIWeaver

What is APIWeaver?

APIWeaver is a Model Context Protocol (MCP) server that fastmcp server that dynamically creates mcp (model context protocol) servers from web api configurations. this allows you to easily integrate any rest api, graphql endpoint, or web service into an mcp-compatible tool that can be used by ai assistan It connects AI assistants to external tools and data sources through a standardized interface.

How do I install APIWeaver?

Follow the installation instructions on the APIWeaver GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with APIWeaver?

APIWeaver works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is APIWeaver free to use?

Yes, APIWeaver is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More APIs MCP Servers

Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "apiweaver": { "command": "npx", "args": ["-y", "apiweaver"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide โ†’

Ready to use APIWeaver?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides