What MCP methods does Mcp Test Add implement?
It implements `initialize`, `tools/list`, and `tools/call` as per the MCP JSON‑RPC specification.
@Djyeigner
暂无概览
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Mcp Test Add is a lightweight test server that implements the MCP (Model Context Protocol) JSON-RPC endpoints for initialize, tools/list, and tools/call. It provides two basic arithmetic tools (add and minus) and is intended for developers testing MCP client‑server interactions.
Install dependencies with pip install -r requirements.txt, then run with uvicorn app:app --reload. Alternatively, build the Docker image with docker build -t mcp-test . and run with docker run -p 8081:8081 mcp-test. Use curl POST requests to http://localhost:8081/ to call MCP methods (e.g., tools/list, tools/call for add or minus).
initialize, tools/list, and tools/call MCP methodsadd and minus arithmetic toolsadd and minus operationsIt implements `initialize`, `tools/list`, and `tools/call` as per the MCP JSON‑RPC specification.
Two tools: `add` (adds two numbers `a` and `b`) and `minus` (subtracts `b` from `a`).
Install Python dependencies from `requirements.txt` and start with `uvicorn app:app --reload`, or use the provided Dockerfile to build and run a container on port 8081.
It uses HTTP as the transport layer, listening on port 8081. All MCP messages are sent via JSON‑RPC over HTTP POST.
No. The README describes it as a test server for protocol testing and prototyping; it is not intended for production use.

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
评论