mcpField
M
MCP Server SDK

MCP Server SDK

Local
github.com/peter-jerry-yeDeveloper Tools5Updated 71w ago

About MCP Server SDK

MCP Server SDK is a work-in-progress MoonBit implementation for building running MCP servers. It supports Wasm Component Model and native backends, with tools and prompts as server capabilities.

Key features

  1. 01MoonBit MCP implementation
  2. 02Wasm Component Model backend
  3. 03Native backend
  4. 04Tools and prompts
  5. 05Stdio transport

Use cases

  1. 01Develop MCP servers in MoonBit
  2. 02Build the Wasm weather example
  3. 03Build a native-backend server

MCP support

The SDK builds MCP servers and supports version 2024-11-05 over Stdio. Servers can provide tools and prompts and call the client's roots capability.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

MCP Server SDK

A WIP MoonBit implementation to support Model Context Protocol.

Supported backends:

  • Wasm's Component Model
  • Native backend

and more (as long as an implementation exists for peter-jerry-ye/async/stream).

The user can use this to develop a running MCP server, providing more functionality to their AI models.

Currently Supported Features

Version:

  • 2024-11-05

Transport:

  • Stdio

Provide server capabilities:

  • Tools
  • Prompts

Call client capabilities (if provided):

  • List roots

Example

See ./example for a simple weather MCP server in Wasm, and ./example-c for a simple MCP server in native backend.

TODO

  • Add documentation
  • Add tests
  • Support more features
  • Better error handling and better UX

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.