Token导航 LogoToken导航

MCP 工具与服务目录

找到适合你的 MCP Server,快速完成接入

按功能、传输方式和来源整理 MCP Server,提供安装命令、配置方式、仓库与文档入口,方便你快速比较并接入合适的服务。

正式条目

87,640

可复制安装

36,828

最近生成

2026-05-22

开发工具未说明

Provides real-time access to menus from all six MIT Bon Appétit dining halls. It enables users to query daily or weekly schedules and filter options by specific dietary requirements such as vegan, halal, or gluten-free.

开发工具未说明

Provides comprehensive access to the MITRE ATT\&CK knowledge base with 50+ tools for querying threat actors, malware, and techniques, including automatic ATT\&CK Navigator layer generation for threat analysis and visualization.

开发工具未说明

A server that interfaces with the Mixpanel API, allowing users to query events data, retention, and funnels through natural language from any MCP client like Cursor or Claude Desktop.

开发工具未说明

Enables creation and management of professional email templates using MJML markup language. Provides compilation to responsive HTML, template generation, validation, and component documentation for building email campaigns.

开发工具未说明

MCP server bridging product ideas to prioritized roadmaps + spec drafts. Hands directly off to mk-spec-master. (AI 規劃大師)

开发工具未说明

mcp-test-runner is an MCP server that lets your AI client (Claude / Cursor / Codex / Gemini) drive your entire QA loop end-to-end: * Run tests across pytest / Jest / Cypress / Go / Maestro — single MCP surface, one env var to switch * Analyze a URL (Web DOM probe) or a live mobile screen (Maestro hierarchy) to extract testable modules + candidate cases * Generate runna

开发工具未说明

AI 規格大師 — MCP server bridging specs (Linear / JIRA / GitHub Issues / Notion / Markdown / Figma) to tests, with bidirectional traceability and a spec-quality coach. Sibling to mk-qa-master.

开发工具未说明

A Cloudflare Worker that provides access to MLB Statistics API data through the Model Context Protocol, supporting multiple endpoints like team info, player stats, game schedules, and live game data.

开发工具未说明

Execute Python code with persistent state across Claude conversations using a background Jupyter kernel. Supports creating notebooks, managing virtual environments, and maintaining variables/imports between code executions.

开发工具未说明

Enables routing of ML tasks like chat, sentiment analysis, recommendations, and summarization to appropriate models through a dynamic YAML-based registry. Provides async FastAPI endpoints with streaming support, retry logic, and pluggable model architecture for scalable ML inference.

开发工具未说明

A minimal Model Context Protocol (MCP) server that uses streamable HTTP transport to provide demo tools for calculations, notes, and time. It serves as a standalone example for testing MCP connectivity and gateway registration through a standard HTTP endpoint.

其他未说明

Enables LLMs to access M/M/1 queuing theory resources, validate parameters, calculate theoretical metrics, generate and execute SimPy simulations, and compare simulation results with theoretical predictions.

开发工具未说明

Provides comprehensive M/M/1 queuing system simulation capabilities including theoretical calculations, parameter validation, SimPy simulation execution, and comparison of simulation results with theoretical metrics.

开发工具未说明

An MCP server that connects AI assistants to a local Wolfram Engine, enabling symbolic math, numerical analysis, and data visualization through Wolfram Language. It provides secure expression filtering, client authentication, and supports both local stdio and HTTP transports.

开发工具未说明

Provides human-like memory dynamics for AI assistants where memories naturally fade over time unless reinforced through use, mimicking the Ebbinghaus forgetting curve. Enables automatic saving, searching, and management of contextual information with temporal decay algorithms.

开发工具未说明

Turns text prompts into premium iOS UI mockups (PNG + HTML). Powered by Claude + a Playwright headless renderer. Two backends: local claude CLI (uses your Claude Code subscription) or the Anthropic API.

开发工具未说明

MCP server for mockzilla. Lets coding agents (Claude Desktop, Cursor, etc.) install the mockzilla CLI, stand up API mocks from an OpenAPI spec or a single endpoint, and — with an account — deploy hosted mocks on mockzilla.org.