发现优秀的 MCP 服务器

@staticpayload/gemini-mcp

Bridges Google's Gemini CLI to MCP-compatible AI assistants, enabling prompt execution, model listing, and raw CLI commands.

che-word-mcp

Swift-native MCP server for Word (.docx) document manipulation. 148 tools for creating, reading, editing, formatting, and exporting Word documents with full OOXML support.

overleaf-paper-mcp

MCP server for managing academic LaTeX projects in Overleaf: create projects, transfer files, compile documents, inspect compiler output, and download PDFs.

MailInApp for Claude Desktop

Enables Claude Desktop to interact with MailInApp projects, campaigns, and contacts. Allows designing and reading interactive email results with explicit confirmation for sending real campaigns.

Odoo Index MCP

Enables AI agents to search and retrieve details about Odoo code elements (models, fields, views, etc.) with exact file locations using MCP tools.

AkShare MCP Server

Enables querying Chinese A-share and index financial data, including real-time quotes, historical bars, and index snapshots, with built-in fallback for unstable endpoints.

mcp-on-edge1111

MCP server deployed on EdgeOne Pages, providing a Streamable HTTP MCP server for intelligent chat applications with tool capabilities like generating webpages.

Codebase Intelligence MCP Server

An MCP server that indexes a local Python codebase into a SQLite graph for hybrid code search, file context, lazy explanations, dependency traces, and version-aware symbol history.

Sleeper Fantasy MCP

Enables comprehensive Sleeper Fantasy Football integration with Claude, providing real-time player projections, historical performance analytics, league management, and waiver wire analysis. Supports advanced NFL metrics, lineup optimization, and matchup analysis for fantasy football decision-making.

simple-vision-mcp

A lightweight MCP server for image analysis using any OpenAI-compatible API endpoint, enabling AI agents to analyze images via a single tool.

nexus-mcp

MCP server that lets AI models invoke CLI agents (Gemini, Codex, Claude, OpenCode) as tools — with parallel execution, retries, and structured output parsing.

Enhanced Home Assistant MCP

Enables comprehensive control and monitoring of Home Assistant smart home devices, automations, scenes, and system management through AI assistants. Supports lights, climate, media players, notifications, history tracking, and advanced automation workflows.

Screener MCP Server

MCP server for Indian stock market data — search companies, analyze fundamentals, compare stocks, browse sectors and screens.

cogvideox-drama-mcp

An MCP server that turns drama scripts into storyboard shots and generates videos for each shot using Zhipu CogVideoX, returning timed download URLs. It can be integrated with MCP-compatible agents like LangChain, Dify, Cline, and Cherry Studio.

Sentinel MCP Server

Sentinel is an enterprise-grade security server that integrates tools like Semgrep, Trivy, and Gitleaks via Docker to perform automated vulnerability scanning and compliance checks. It enables users to conduct static analysis, secret detection, and AI-powered threat modeling directly through Model Context Protocol-compatible IDEs.

一个基于Blender-mcp的研究项目，自学记录用( Blender-mcp详情见

好的，我将尽力帮助你理解 Blender-mcp 项目，判断其能力边界，理解 mcp 架构，并尝试添加新功能。 首先，我们需要明确几个步骤： 1. **理解 Blender-mcp 项目:** * **项目目标:** 了解该项目旨在解决什么问题，例如：多客户端协作、版本控制、资源管理等。 * **核心功能:** 掌握项目已经实现的功能，例如：场景同步、资产共享、实时聊天等。 * **技术栈:** 了解项目使用的编程语言、框架、库等，例如：Python、Blender API、网络协议等。 * **代码结构:** 熟悉项目的代码组织方式，例如：客户端、服务器端、数据模型等。 2. **判断能力边界:** * **现有功能的局限性:** 思考现有功能在哪些方面存在不足，例如：同步速度、稳定性、可扩展性等。 * **不支持的功能:** 识别项目尚未实现，但可能对用户有价值的功能，例如：高级冲突解决、权限管理、插件支持等。 * **性能瓶颈:** 分析项目在处理大规模场景或高并发请求时可能遇到的性能问题。 3. **理解 mcp 架构:** * **架构模式:** 确定项目采用的架构模式，例如：客户端-服务器、P2P、混合模式等。 * **组件划分:** 了解项目由哪些核心组件构成，例如：同步引擎、数据存储、通信模块等。 * **数据流:** 跟踪数据在不同组件之间的流动方式，例如：场景数据如何从客户端同步到服务器端。 * **扩展点:** 识别架构中可以方便地添加新功能的扩展点，例如：插件接口、自定义数据类型等。 4. **尝试添加新功能:** * **选择功能:** 基于对项目和架构的理解，选择一个具有可行性和价值的新功能。 * **设计方案:** 设计新功能的实现方案，包括：数据结构、算法、用户界面等。 * **编码实现:** 编写代码实现新功能，并进行测试和调试。 * **集成测试:** 将新功能集成到现有项目中，并进行全面的测试。 **具体步骤和建议:** * **阅读项目文档:** 仔细阅读 Blender-mcp 项目的 README 文件、API 文档、设计文档等，了解项目的背景、目标、架构和使用方法。 * **运行项目:** 尝试运行 Blender-mcp 项目，体验其现有功能，并观察其运行状态。 * **阅读源代码:** 阅读 Blender-mcp 项目的源代码，理解其实现细节，并学习其编程风格。 * **调试项目:** 使用调试器调试 Blender-mcp 项目，跟踪代码的执行流程，并查找潜在的问题。 * **参与社区:** 加入 Blender-mcp 项目的社区，与其他开发者交流，并寻求帮助。 * **从小处着手:** 从简单的功能开始，逐步增加复杂性，避免一开始就尝试修改核心架构。 * **编写测试用例:** 为新功能编写测试用例，确保其正确性和稳定性。 * **提交代码:** 将新功能的代码提交到 Blender-mcp 项目的仓库，并接受代码审查。 **关于添加新功能的建议:** * **冲突解决:** 改进现有的冲突解决机制，例如：支持更细粒度的冲突检测、提供更友好的冲突解决界面。 * **权限管理:** 添加权限管理功能，允许用户控制其他用户对场景的访问和修改权限。 * **版本控制:** 集成版本控制系统，例如：Git，允许用户回滚到之前的版本。 * **插件支持:** 提供插件接口，允许开发者扩展 Blender-mcp 的功能。 * **性能优化:** 优化同步算法，减少网络延迟，提高同步速度。 **翻译:** 通过学习 Blender-mcp 项目，判断其能力边界，并理解 mcp 架构，尝试添加新的功能。 通过学习 Blender-mcp 项目，判断其能力边界，并理解 mcp 架构，尝试添加新的功能。 **中文翻译:** 通过学习 Blender-mcp 项目，判断其能力边界，并理解 mcp 架构，尝试添加新的功能。 **更自然的中文翻译:** 通过研究 Blender-mcp 项目，确定它的能力范围，理解其 mcp 架构，并尝试添加新的功能。 希望这些信息能帮助你更好地理解 Blender-mcp 项目，并成功添加新功能。祝你一切顺利！

nexudus-mcp

Enables natural language booking and management of rooms in Nexudus coworking spaces, including listing rooms, checking availability, booking, viewing/cancelling bookings, and schedules.

renef-mcp

MCP server for Renef, providing dynamic instrumentation and reverse engineering capabilities for Android ARM64, including native hooking, Java interception, and memory manipulation.

Funding & Press Signal Scanner MCP Server

Scans public news and press for a company's funding rounds, executive moves, product launches, acquisitions, partnerships, and IPOs, returning deduplicated events in flat JSON.

Unified Agent Context System

A highly configurable MCP server with modular architecture supporting portfolio management and test tools over HTTP or stdio transport.

jlc-mcp

Local Model Context Protocol server that exposes EasyEDA Pro design capabilities as MCP tools, enabling project inspection, schematic editing, PCB design, validation, and manufacturing exports through natural language.

SuperCMO Skills

Open-source skills that empower any AI agent (Claude, Cursor, Codex, Hermes, etc.) to generate end-to-end marketing campaigns — UGC videos, ad videos, product photography and more. From a product photo and a brief it casts AI actors, picks the best models, and edits finished assets of any length with consistent actor and product. It also researches competitors, publishes, and reviews performance.

FlipperTalk

Talk to your Flipper Zero from Claude Code — or any MCP client. Storage, app deployment, screen capture, button automation, JavaScript execution on the device, and honest answers about what is nearby.

io.github.rcsb/rcsb-mcp

Enables discovery, inspection, and cross-referencing of Protein Data Bank structures through three RCSB APIs: search, data, and sequence coordinates.

Smithery Registry OpenAPI Server

用于 Smithery Registry 的 OpenAPI 服务器，提供对 MCP 服务器的访问

Kickd MCP Server

Enables Claude Code to manage automations, tasks, skills, workflows, credentials, variables, webhooks, events, and notifications within the kickd background automation daemon.

vidsight

Enables AI agents to query local video timelines by extracting speech, frame captions, and on-screen text into a SQLite store, exposing search and retrieval tools via MCP.

API to MCP

Converts any REST API endpoints into MCP tools, enabling AI clients like Cursor and Claude Desktop to call internal services directly.

Slander MCP

An MCP server that retrieves and ranks humorous roasts, jokes, and memes about real or fictional characters from Twitter/X. It leverages LLMs for intelligent query generation and uses social engagement metrics to identify and rank high-quality content.

MCP Empe Server

Enables users to manage self-sovereign identity credentials by creating schemas, issuing verifiable credentials, generating verification QR codes, and checking verification status via the Empe SSI ecosystem.