mcpsvr
Discover Exceptional MCP Servers
claude mcp add --transport stdio nanbingxyz-mcpsvr node server.js \ --env PORT="3000" \ --env NODE_ENV="production"
How to use
MCPSvr functions as a centralized directory for MCP servers. It hosts a collection of server configurations that enable MCP clients (like 5ire) to discover, install, and run community-created MCP server implementations directly from the directory. The repository maintains a JSON-based registry at /public/servers.json which catalogs each registered MCP server with its execution environment, runtime arguments, and optional environment variables. To use MCPSvr, browse the directory of available servers, review their configuration details (name, key, description, command, args, env, and homepage), and then deploy a chosen server in your environment using its specified runtime (for example Node.js, UVX, Python, etc.). The system is designed to support interactive parameter needs via a standardized parameter extraction format, facilitating integration into client tooling and automated workflows.
In practice, you would select a server entry, understand its command and arguments, ensure required environment variables are set, and then start the server using the recommended runtime command. The homepage field provides official documentation or repository links for deeper guidance on each server’s capabilities and usage patterns. This setup enables MCP clients to install and run servers with minimal friction, promoting a plug-and-play ecosystem for community contributions.
How to install
Prerequisites:
- A supported runtime environment (Node.js for node-based servers, Python/uv for uvx-based servers, etc.).
- Git for cloning the repository.
- Basic command-line proficiency.
Step-by-step installation:
-
Clone the MCPSvr repository: git clone https://github.com/nanbingxyz/mcpsvr.git cd mcpsvr
-
Install dependencies (Node.js example): npm install
-
Verify the setup and run the server (Node.js example):
Start the MCP server
node server.js
Optional: use a process manager or npm script if provided, e.g., npm run start
-
Alternatively, if using a different runtime (example UVX for Python-based servers):
Install and run according to the project’s runtime guidelines
e.g., uvx install / run as documented in the server’s homepage
-
Validate the server is running by accessing the configured port (default 3000) and checking /public/servers.json for registered MCP entries.
Notes:
- Ensure your environment variables (as defined in the server’s mcp_config entry) are correctly set before starting.
- If you are contributing a new MCP server, add its configuration to /public/servers.json following the provided schema.
Additional notes
Tips and common issues:
- The centralized registry /public/servers.json must stay synchronized with registered MCP servers; submit PRs to add or update entries.
- If a server entry fails to start, verify that the runtime and arguments match the server’s expected invocation. Check the env field for required variables and set them in your environment.
- Always review the homepage/documentation linked in each server entry for specific runtime requirements, version compatibility, and security considerations.
- When contributing, maintain alphabetical ordering of configuration keys and ensure the identifier (key) starts with a letter and is alphanumeric, as per the contribution guidelines.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
anytype
An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
tableau
Tableau's official MCP Server. Helping Agents see and understand data.
mcp -circleci
A specialized server implementation for the Model Context Protocol (MCP) designed to integrate with CircleCI's development workflow. This project serves as a bridge between CircleCI's infrastructure and the Model Context Protocol, enabling enhanced AI-powered development experiences.
one-search
🚀 OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.
kollektiv
Kollektiv MCP enables you to chat with and query your own documents directly from IDEs and MCP clients. Private, secure, and integrated into your favorite code editor