Crimson Crab Template MCP server

Claude-powered MCP server in Rust (starter template)

A minimal, production-ready Model Context Protocol (MCP) server, written in Rust, backed by Anthropic's Claude API through the crimson-crab SDK. It exposes five tools: askclaude (send a prompt, get Claude's reply), chat (multi-turn conversation), counttokens (price a prompt without running it), listmodels (enumerate the models your API key can use), and getmodel (limits and metadata for one model).

Use it as the reference starting point for building your own Claude-powered MCP tools in Rust.

Use this template

Click Use this template on GitHub, or generate a fresh project with cargo generate:

cargo generate --git https://github.com/singhpratech/crimson-crab-mcp-template

You can also just clone it:

git clone https://github.com/singhpratech/crimson-crab-mcp-template

Quickstart

export ANTHROPIC_API_KEY=sk-ant-...
cargo run

The server communicates over stdio, so running it directly just waits for an MCP client to connect. All logging goes to stderr — stdout is reserved for the MCP protocol. Set RUST_LOG=debug for more verbose logs.

To build an optimized binary you can point a client at:

cargo build --release
# -> target/release/crimson-crab-mcp-template

Wire it into Claude Desktop

Add an entry to your Claude Desktop MCP config (claudedesktopconfig.json), pointing at the built binary and passing your API key through the environment:

{
  "mcpServers": {
    "claude-via-crimson-crab": {
      "command": "/absolute/path/to/target/release/crimson-crab-mcp-template",
      "env": {
        "ANTHROPIC_API_KEY": "sk-ant-..."
      }
    }
  }
}

Restart Claude Desktop; the askclaude, chat, counttokens, listmodels, and getmodel tools will then be available.

The tools

ask_claude

Builds a Claude Messages request (defaulting to the claude-opus-5 model), calls the API, and returns the concatenated text of Claude's reply.

chat

Sends the whole message history to Claude and returns the next reply — use it instead of ask_claude when the caller needs to keep context across turns.

count_tokens

Shortened. The full README is on GitHub.