APIWeaver

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 assistants like Claude.

• 🚀 Dynamic API Registration: Register any web API at runtime
• 🔐 Multiple Authentication Methods: Bearer tokens, API keys, Basic auth, OAuth2, and custom headers
• 🛠️ All HTTP Methods: Support for GET, POST, PUT, DELETE, PATCH, and more
• 📝 Flexible Parameters: Query params, path params, headers, and request bodies
• 🔄 Automatic Tool Generation: Each API endpoint becomes an MCP tool
• 🧪 Built-in Testing: Test API connections before using them
• 📊 Response Handling: Automatic JSON parsing with fallback to text
• 🌐 Multiple Transport Types: STDIO, SSE, and Streamable HTTP transport support

APIWeaver supports three different transport types to accommodate various deployment scenarios:

• Usage: apiweaver run or apiweaver run --transport stdio
• Best for: Local tools, command-line usage, and MCP clients that connect via standard input/output
• Characteristics: Direct process communication, lowest latency, suitable for desktop applications
• Endpoint: N/A (uses stdin/stdout)

• Usage: apiweaver run --transport sse --host 127.0.0.1 --port 8000
• Best for: Legacy MCP clients that only support Server-Sent Events
• Characteristics: HTTP-based, one-way streaming from server to client
• Endpoint: http://host:port/mcp
• Note: This transport is deprecated in favor of Streamable HTTP

• Usage: apiweaver run --transport streamable-http --host 127.0.0.1 --port 8000
• Best for: Modern web deployments, cloud environments, and new MCP clients
• Characteristics: Full HTTP-based com