What are the prerequisites?
Node.js installed, Claude for MacOS (download from Anthropic), and basic understanding of local servers and MCP tools.
@sunmer
基本信息
Simple MCP server using Claude to interact with a local JSON server
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。
A basic setup guide that demonstrates how to use Claude (MacOS desktop) to interact with a local mock JSON server via the Model-Computer Protocol (MCP). It is intended for developers learning how to integrate MCP tools with a local API.
Install dependencies with npm install, then run npm run mock-api and npm run mcp-server. Edit the claude_desktop_config.json file to add the MCP server configuration, restart Claude, and prompt it with commands like "get all posts" or "insert a post with id 500, title 'created by claude' and views 123".
Node.js installed, Claude for MacOS (download from Anthropic), and basic understanding of local servers and MCP tools.
Run `npm install` in the project root, then `npm run mock-api` to start the JSON server and `npm run mcp-server` to start the MCP server.
Edit the `claude_desktop_config.json` file (usually in `~/.claude/` or the app’s internal config folder) and add the MCP server configuration with the command `node` and the absolute path to `dist/index.js`.
Two new MCP tools marked with a 🛠️ hammer icon appear below the input bar.
Run `npx @modelcontextprotocol/inspector node build/index.js` and view the available resources at `http://127.0.0.1:6274/#resources`.

Blog MCP server for AI agents. One signup call returns a blog, an API key and a live URL; then your agent publishes markdown posts and gets public URLs back. Your agent does the writing; you get a dashboard for stats.
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

Hire a verified local human for small real-world tasks your AI agent can't do: errands, queues, pickups, in-person checks and on-site photos. Your agent posts a quest, local humans send offers, and your user picks one an
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.
评论