发现优秀的 MCP 服务器

mcp-arcgis-vilas

Enables querying and searching Vilas County, Wisconsin open geospatial datasets (parcels, addresses, zoning) via ArcGIS services using natural language or direct tool calls.

fec-mcp-server

Query FEC campaign finance data — search candidates, track donations, analyze spending, and monitor Super PAC activity via the OpenFEC API.

gdrive-rag-mcp

Enables Google# MyData from (JSON (server name is

Wechat Devtools MCP

Enables AI assistants to control WeChat mini-programs running in WeChat Developer Tools through MCP tools. Provides automation capabilities for launching, navigating, querying, and interacting with pages and elements.

Local Lens

A 100% local development monitoring tool that captures browser console logs, network requests, and backend server output for analysis by AI assistants via MCP. It enables LLMs to debug applications by providing structured, real-time access to full-stack log data and persistent local storage.

@volter/tunnel-mcp

Enables AI agents to manage account, usage, and abuse operations for the Volter tunnel relay.

theo-van-gogh-mcp

MCP server that lets AI assistants manage an art catalogue — find paintings, post to social media, upload to galleries, schedule posts, and update metadata.

mcp-mbta

Enables real-time access to Boston MBTA transit data (subway, bus, commuter rail, etc.) via the MBTA v3 API.

Odybook MCP Server

Enables AI assistants to search tours, check availability, and manage bookings via Odybook's experience management platform.

basecamp-mcp-server

Enables AI assistants to interact with Basecamp projects, messages, to-dos, and Card Tables, with read-only access by default and write operations requiring explicit approval.

postgres-mcp-server

A Model Context Protocol server that provides secure database access to PostgreSQL through Kysely ORM, enabling natural language interaction with PostgreSQL databases. It offers 40+ MCP tools for querying, schema inspection, diagnostics, and Java backend monitoring.

Kimi Partner

Enables Codex to delegate scoped frontend implementation tasks to Kimi, while Codex retains task planning, review, and acceptance.

Logo-Analyze

An MCP server for intelligent logo extraction and processing, supporting automatic recognition and extraction of logo icons from website URLs, and providing image processing and vector conversion functions.

mcp-osint

MCP server that provides access to 14 OSINT data sources including government, research, corporate, and news APIs, enabling search, preview, and retrieval of public intelligence data.

MCP-Suno

MCP server for Suno music generation API that enables generating lyrics and custom songs with style tags, model selection, and automatic polling for task completion.

Snowflake MCP Server

Enables AI assistants to securely connect to Snowflake data warehouses and execute SQL queries through natural language interactions. Supports multiple authentication methods and provides formatted query results with built-in security controls.

Awesome MCP Security

Okay, here's a translation of "Security Threats related with MCP (Model Context Protocol), MCP Servers and more" into Chinese, along with some expanded explanations of the potential security threats to help you understand the context better: **Translation:** **中文 (Chinese):** 与 MCP (模型上下文协议)、MCP 服务器及相关内容相关的安全威胁 **Explanation of Potential Security Threats (to help with understanding and context):** To fully understand the security threats, it's important to consider what MCP is and how it's used. Since "Model Context Protocol" isn't a widely known or standardized term, I'll assume it refers to a protocol used to share context or data related to machine learning models. Based on that assumption, here are some potential security threats: * **Data Poisoning:** * **中文 (Chinese):** 数据投毒 (Shùjù tóudú) * **Explanation:** If an attacker can inject malicious data into the MCP server or the data used to train or evaluate the models, they can corrupt the models' behavior. This could lead to the model making incorrect predictions or decisions, potentially causing harm. * **Model Inversion Attacks:** * **中文 (Chinese):** 模型反演攻击 (Móxíng fǎnyǎn gōngjí) * **Explanation:** An attacker might try to reconstruct sensitive training data by querying the model through the MCP server. If the model reveals too much information about the training data, it could compromise privacy. * **Model Extraction Attacks:** * **中文 (Chinese):** 模型提取攻击 (Móxíng tíqǔ gōngjí) * **Explanation:** An attacker could try to create a copy of the model by observing its behavior through the MCP server. This is especially concerning if the model is proprietary or contains valuable intellectual property. * **Denial of Service (DoS) Attacks:** * **中文 (Chinese):** 拒绝服务攻击 (Jùjué fúwù gōngjí) * **Explanation:** An attacker could flood the MCP server with requests, making it unavailable to legitimate users. * **Unauthorized Access:** * **中文 (Chinese):** 未授权访问 (Wèi shòuquán fǎngwèn) * **Explanation:** If the MCP server is not properly secured, unauthorized users could gain access to sensitive data or models. This could involve exploiting vulnerabilities in the server software or using stolen credentials. * **Man-in-the-Middle (MitM) Attacks:** * **中文 (Chinese):** 中间人攻击 (Zhōngjiān rén gōngjí) * **Explanation:** An attacker could intercept communication between clients and the MCP server, potentially eavesdropping on sensitive data or modifying requests and responses. * **Vulnerabilities in MCP Server Software:** * **中文 (Chinese):** MCP 服务器软件中的漏洞 (MCP fúwùqì ruǎnjiàn zhōng de lòudòng) * **Explanation:** The MCP server software itself might contain security vulnerabilities that attackers could exploit to gain control of the server or access sensitive data. * **Injection Attacks (e.g., SQL Injection, Command Injection):** * **中文 (Chinese):** 注入攻击 (Zhùrù gōngjí) (例如，SQL 注入，命令注入) * **Explanation:** If the MCP server uses user-supplied input without proper sanitization, attackers could inject malicious code into the server's database queries or operating system commands. * **Authentication and Authorization Issues:** * **中文 (Chinese):** 身份验证和授权问题 (Shēnfèn yànzhèng hé shòuquán wèntí) * **Explanation:** Weak authentication mechanisms or flawed authorization policies could allow unauthorized users to access or modify data and models. **In summary, the security threats related to MCP, MCP servers, and related content are diverse and depend heavily on the specific implementation and use case. It's crucial to implement robust security measures to protect against these threats.** If you can provide more details about the specific context of MCP in your situation, I can provide a more tailored and accurate translation and explanation.

Jokes MCP Server

An MCP server that retrieves jokes from three different sources: Chuck Norris jokes, Dad jokes, and Yo Mama jokes.

qa-ai-mcp-server-gits

MCP server for end-to-end QA automation: generates test scenarios, discovers Playwright locators, creates TypeScript test code, executes tests, and creates GitHub issues for failures.

WebMCP Contract Portfolio

An MCP server that lets Claude directly operate a commercial insurance contracts app through WebMCP, enabling natural-language queries, renewals, updates, and reporting against live React state and Postgres.

CloudVision MCP Server

Enables querying and interacting with Arista CloudVision via MCP, supporting both HTTP and gRPC connections.

OpenLMlib

Provides AI assistants with a local knowledge base and research library, enabling semantic and full-text retrieval, memory persistence, and multi-agent collaboration via 58 MCP tools.

CME Prediction Markets MCP Server

Enables verification of natural language claims against CME prediction market data, with tools to query historical trading data, get contract information, and automatically verify claims using NLP-powered parsing.

notebooklm-mcp

MCP server for Google NotebookLM enabling notebook, source, and audio overview management with hybrid metadata storage.

HERO MCP

MCP server for HERO handyman software, providing 34 OAuth-secured read/write tools with multi-tenant support and built-in API correctness checks.

automatelab-ai-seo

Vendor-agnostic MCP server that audits, scores, and rewrites web pages for AI-citation eligibility. No API keys. No registration. Works in Claude Desktop, Cursor, Cline, Windsurf, VS Code (Copilot / Continue), and any client that speaks the Model Context Protocol.

opencode-chromium

Provides Chromium browser automation for MCP clients and AI agents, enabling background tab control, observation, session management, and performance diagnostics through tools like browser_run and browser_observe.

slab-mcp

MCP server for analyzing Clay tables — schema, rows, errors, and enrichment debugging, using the internal Clay API to enable AI assistants to understand and debug Clay tables.

WikiJS MCP Server

An MCP server that enables full management of WikiJS instances, supporting operations like page creation, searching, and updating. It also provides tools for knowledge graph exploration, content summarization, and retrieval of wiki statistics.

Doco

Doco is an open-source collaborative document workspace where humans and AI agents write together. Its MCP server gives Claude Code and Cursor stable block-level addressing, version-protected writes, Markdown round-trip, and shared access to the same live documents.