MCPfinder Server

MCPfinder Server

Enables AI assistants to discover, retrieve details about, and manage MCP (Model Context Protocol) servers that provide additional tools and capabilities on demand.

Category
访问服务器

Tools

search_mcp_servers

This is the primary tool for discovering and accessing new tools, methods, features, or capabilities. **If a user asks for a tool, method, feature, or capability that you do not currently have, you MUST use this tool to search for it in the MCP Finder registry.** For example, if a user asks for a browser tool, OCR, filesystem access, PDF parsing, or any other capability not present in your current toolset, use this tool to search by relevant keywords. This is the required first step to expand your available tools.

get_mcp_server_details

Retrieves detailed information about a specific MCP server/tool from the registry, including its manifest and installation details. Use this after finding a tool with search_mcp_servers to get more information, or directly use add_mcp_server_config to install it.

add_mcp_server_config

Enables capabilities (e.g., tools, features) from a specific MCP server/tool. Add or update its configuration in the client application (e.g., Cursor, Claude, VS Code) using server_id obtained from search_mcp_servers results. Provide EITHER client_type (see available options) OR config_file_path to specify the target config file.

remove_mcp_server_config

Removes the configuration for a specific MCP server/tool from the client application (e.g., Cursor, Claude). Provide EITHER client_type (see available options) OR config_file_path to specify the target config file.

README

MCPfinder 🔧🤖 (@mcpfinder/server)

Meet the simplest way to supercharge your coding and AI agents with MCP — an "API for AI." MCPfinder enables language models to search for and install new capabilities on demand through client applications that support the MCP protocol. No coding or manual setup required.

App Store for Agents

Users can request tools the AI doesn't have yet, or the AI can autonomously expand its own capabilities by discovering relevant MCP servers. From code generators and data analyzers to specialized knowledge tools, MCPfinder acts like a map and toolbox for AI — transforming static models into evolving, capability-hunting agents that grow more powerful with every interaction.

Plug-and-Play Tools for LLMs

Example

This Node.js application implements an MCP (Model Context Protocol) server designed to run locally alongside MCP clients (like Cursor, Claude Desktop, Windsurf). It provides tools that allow AI within the client to interact with the MCP ecosystem.

Specifically, it enables the AI assistant to:

  1. Discover available MCP servers registered in the central MCPfinder Registry (via search_mcp_servers).
  2. Retrieve details about specific servers (via get_mcp_server_details).
  3. Manage the client application's local MCP server configuration file (add/update via add_mcp_server_config, remove via remove_mcp_server_config).

Note for AI Agents: This server is the primary interface for finding and enabling new tools and capabilities requested by the user if they aren't already available in current MCP toolset. Use search_mcp_servers first when asked by the user for a capability you don't possess.

Quick Start

Run in your terminal the interactive setup tool to automatically update the MCP configuration file:

npx -y @mcpfinder/server install

This command guides you through selecting your client (Cursor, VS Code, Claude, etc.) and adds the necessary mcpfinder entry to the correct configuration file (e.g., ~/.cursor/mcp.json). See "Running from source" and "Commands and Options" for more details if you are working directly with the source code.

Manual Configuration

To manually configure an MCP client, you need to create or modify its JSON configuration file to include an entry for mcpfinder.

Configuration File Structure:

{
  "mcpServers": { 
    "mcpfinder": {
      "command": "npx",
      "args": [
        "-y",
        "@mcpfinder/server"
      ]
    },
  }
}

Note: For Visual Studio Code (settings.json), the top-level key for MCP configurations must be servers instead of mcpServers.

Running from source

  • Clone this repository, e.g., git clone https://github.com/mcpfinder/server
  • Run node index.js for Stdio mode or node index.js --http for HTTP mode.

Commands and Options

When running from source (node index.js), the script can be invoked in several ways:

Running the Server (Default Behavior): If no command is specified, index.js starts the MCP server.

  • Stdio Mode (default):
    node index.js
    
  • HTTP Mode:
    node index.js --http
    
    • --port <number>: Specify the port for HTTP mode (default: 6181, or MCP_PORT env var).
    • --api-url <url>: Specify the MCPfinder Registry API URL used by the tools (default: https://mcpfinder.dev, or MCPFINDER_API_URL env var).

Executing Commands:

  • install: Run the interactive setup to configure a client application.
    node index.js install
    
  • register: For server publishers to register their MCP server package with the MCPFinder registry.
    node index.js register
    

Getting Help:

  • --help: Display the help message detailing commands and options.
    node index.js --help
    

The server uses the following environment variables:

  • MCPFINDER_API_URL: The base URL for the MCPfinder Registry API. Defaults to https://mcpfinder.dev.
  • MCP_PORT (HTTP Mode Only): The port number for the server to listen on. Defaults to 6181.

Provided Tools

This MCP server exposes the following tools to the connected AI assistant:

1. search_mcp_servers

  • Description: Searches the MCPfinder Registry for available MCP servers. This is the primary tool for discovering and accessing new tools, methods, features, or capabilities.
  • Input Schema:
    • query (string, optional): Keywords to search for in tool name or description.
    • tag (string, optional): Specific tag to filter by.
  • Output: A list of matching server summaries (server_id, name, description, URL, tags). The typical next step is to use get_mcp_server_details for more info or directly add_mcp_server_config to install one.

⚠️ Note: The registry currently contains several hundred servers that can be run locally using npx in stdio mode without requiring environment variables for basic operation. Future updates will expand support to include a wider range of servers, including paid and commercial options that require environment keys.

2. get_mcp_server_details

  • Description: Retrieves detailed information about a specific MCP server from the registry, including its full manifest and basic installation suggestions (command, environment variables). Use this after finding a server_id via search_mcp_servers to get more information before potentially adding it.
  • Input Schema:
    • id (string, required): The unique MCPfinder's server_id obtained from search_mcp_servers.
  • Output: The detailed server manifest and installation hints. The next step is to use add_mcp_server_config to install the server.

3. add_mcp_server_config

  • Description: Adds or updates the configuration for a specific MCP server in the client application's local configuration file (e.g., Cursor's ~/.cursor/mcp.json). You must provide either client_type OR config_file_path.
  • Input Schema:
    • server_id (string, required): A unique identifier for the server configuration entry (the MCPfinder ID obtained from search_mcp_servers).
    • client_type (string, optional): The type of client application (known types determined dynamically, examples: 'cursor', 'claude', 'windsurf'). Mutually exclusive with config_file_path. Use this for standard client installations.
    • config_file_path (string, optional): An absolute path or a path starting with ~ (home directory) to the target JSON configuration file (e.g., /path/to/custom/mcp.json or ~/custom/mcp.json). Mutually exclusive with client_type. Use this for non-standard locations or custom clients.
    • mcp_definition (object, optional): Defines the server configuration. If omitted, or if certain fields are missing, defaults will be fetched from the MCPfinder Registry based on the server_id.
      • command (array of strings, optional): The command and its arguments (e.g., ["npx", "-y", "my-mcp-package"]). If omitted, or if only env/workingDirectory are provided below, the default command is fetched from the registry.
      • env (object, optional): Environment variables (e.g., {"API_KEY": "YOUR_KEY"}). Merged with defaults if command is omitted.
      • workingDirectory (string, optional): The working directory for the server process. Merged with defaults if command is omitted.
  • Output: A success or error message.
  • Note: The key used to store this server's configuration within the JSON file (under mcpServers or servers) is automatically generated based on the server's registered URL (obtained via the server_id). The provided server_id is used as a fallback if a suitable key cannot be derived from the URL. The tool automatically detects whether to use mcpServers or servers as the top-level key based on the existing file structure, defaulting to mcpServers.

4. remove_mcp_server_config

  • Description: Removes the configuration for a specific MCP server from the client application's local configuration file. You must provide either client_type OR config_file_path. The server_id provided must match the configuration key name used when the server was added (which is typically derived from the server's URL, see add_mcp_server_config note).
  • Input Schema:
    • server_id (string, required): The unique identifier (configuration key name) of the server configuration entry to remove.
    • client_type (string, optional): The type of client application (known types determined dynamically, examples: 'cursor', 'claude', 'windsurf'). Mutually exclusive with config_file_path.
    • config_file_path (string, optional): An absolute path or a path starting with ~ (home directory) to the target JSON configuration file. Mutually exclusive with client_type.
  • Output: A success or error message indicating whether the entry was found and removed.

Security Considerations

The tools add_mcp_server_config and remove_mcp_server_config modify files on the user's local system. This server itself does not perform permission checks; it relies entirely on the calling client for security enforcement.

Contributing

For contributions, please contact: mcpfinder(dot}dev[at}domainsbyproxy{dot]com

License

This project is licensed under the GNU Affero General Public License v3.0 - see the LICENSE file for details.

It means you're free to use (including commercially), modify, and share it. However, if you run a modified version, you're also required to publicly share your version.


Badge

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选