Discover Awesome MCP Servers
Extend your agent with 84,517 capabilities via MCP servers.
- All84,517
- Developer Tools3,867
- Search1,714
- Research & Data1,557
- AI Integration Systems229
- Cloud Platforms219
- Data & App Analysis181
- Database Interaction177
- Remote Shell Execution165
- Browser Automation147
- Databases145
- Communication137
- AI Content Generation127
- OS Automation120
- Programming Docs Access109
- Content Fetching108
- Note Taking97
- File Systems96
- Version Control93
- Finance91
- Knowledge & Memory90
- Monitoring79
- Security71
- Image & Video Processing69
- Digital Note Management66
- AI Memory Systems62
- Advanced AI Reasoning59
- Git Management Tools58
- Cloud Storage51
- Entertainment & Media43
- Virtualization42
- Location Services35
- Web Automation & Stealth32
- Media Content Processing32
- Calendar Management26
- Ecommerce & Retail18
- Speech Processing18
- Customer Data Platforms16
- Travel & Transportation14
- Education & Learning Tools13
- Home Automation & IoT13
- Web Search Integration12
- Health & Wellness10
- Customer Support10
- Marketing9
- Games & Gamification8
- Google Cloud Integrations7
- Art & Culture4
- Language Translation3
- Legal & Compliance2
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.
gdrive-rag-mcp
Enables Google# MyData from (JSON (server name is
@volter/tunnel-mcp
Enables AI agents to manage account, usage, and abuse operations for the Volter tunnel relay.
Awesome MCP Security
MCP (Model Context Protocol)に関連するセキュリティ脅威、MCPサーバーなどについて: This is a broad topic, so I'll outline some potential security threats related to MCP and MCP servers. The specific threats will depend on the implementation and usage of MCP. * **Data Poisoning:** If an attacker can inject malicious data into the model context, they could influence the behavior of the model in unintended and potentially harmful ways. This is especially concerning if the model is used for critical decision-making. * **Unauthorized Access:** If access to the MCP server is not properly secured, unauthorized users could gain access to sensitive model context data or even modify the model itself. * **Denial of Service (DoS):** An attacker could flood the MCP server with requests, overwhelming its resources and making it unavailable to legitimate users. * **Man-in-the-Middle (MitM) Attacks:** If communication between clients and the MCP server is not encrypted, an attacker could intercept and modify data in transit. * **Injection Attacks:** Depending on how the MCP server processes input, it may be vulnerable to injection attacks (e.g., SQL injection, command injection). * **Vulnerabilities in MCP Server Software:** Like any software, MCP server software may contain vulnerabilities that attackers could exploit. * **Data Leakage:** If the MCP server is not properly configured, sensitive model context data could be leaked to unauthorized parties. * **Model Extraction:** An attacker might try to extract the underlying model from the MCP server, potentially stealing valuable intellectual property. To mitigate these threats, it's important to implement strong security measures, such as: * **Authentication and Authorization:** Ensure that only authorized users can access the MCP server and its data. * **Encryption:** Encrypt communication between clients and the MCP server. * **Input Validation:** Carefully validate all input to the MCP server to prevent injection attacks. * **Regular Security Audits:** Conduct regular security audits to identify and address potential vulnerabilities. * **Keep Software Up-to-Date:** Keep the MCP server software and all related components up-to-date with the latest security patches. * **Data Sanitization:** Sanitize data before it is used to update the model context. * **Rate Limiting:** Implement rate limiting to prevent DoS attacks. * **Access Control Lists (ACLs):** Use ACLs to restrict access to specific resources on the MCP server. The specific security measures that are needed will depend on the specific implementation and usage of MCP. It's important to carefully assess the risks and implement appropriate security controls. --- 日本語訳: MCP(モデルコンテキストプロトコル)に関連するセキュリティ脅威、MCPサーバーなどについて: これは広範なトピックなので、MCPおよびMCPサーバーに関連する潜在的なセキュリティ脅威の概要を説明します。具体的な脅威は、MCPの実装と使用方法によって異なります。 * **データの汚染:** 攻撃者が悪意のあるデータをモデルコンテキストに注入できる場合、モデルの動作に意図しない、潜在的に有害な影響を与える可能性があります。これは、モデルが重要な意思決定に使用される場合に特に懸念されます。 * **不正アクセス:** MCPサーバーへのアクセスが適切に保護されていない場合、許可されていないユーザーが機密性の高いモデルコンテキストデータにアクセスしたり、モデル自体を変更したりする可能性があります。 * **サービス拒否(DoS)攻撃:** 攻撃者がMCPサーバーにリクエストを大量に送り込み、リソースを圧倒し、正当なユーザーが利用できなくなる可能性があります。 * **中間者(MitM)攻撃:** クライアントとMCPサーバー間の通信が暗号化されていない場合、攻撃者は転送中のデータを傍受して変更する可能性があります。 * **インジェクション攻撃:** MCPサーバーが入力を処理する方法によっては、インジェクション攻撃(SQLインジェクション、コマンドインジェクションなど)に対して脆弱である可能性があります。 * **MCPサーバーソフトウェアの脆弱性:** 他のソフトウェアと同様に、MCPサーバーソフトウェアには、攻撃者が悪用する可能性のある脆弱性が含まれている可能性があります。 * **データ漏洩:** MCPサーバーが適切に構成されていない場合、機密性の高いモデルコンテキストデータが許可されていない当事者に漏洩する可能性があります。 * **モデル抽出:** 攻撃者がMCPサーバーから基盤となるモデルを抽出しようとし、貴重な知的財産を盗む可能性があります。 これらの脅威を軽減するには、次のような強力なセキュリティ対策を実装することが重要です。 * **認証と認可:** 許可されたユーザーのみがMCPサーバーとそのデータにアクセスできるようにします。 * **暗号化:** クライアントとMCPサーバー間の通信を暗号化します。 * **入力検証:** インジェクション攻撃を防ぐために、MCPサーバーへのすべての入力を注意深く検証します。 * **定期的なセキュリティ監査:** 潜在的な脆弱性を特定して対処するために、定期的なセキュリティ監査を実施します。 * **ソフトウェアの最新状態維持:** MCPサーバーソフトウェアおよび関連するすべてのコンポーネントを、最新のセキュリティパッチで最新の状態に保ちます。 * **データのサニタイズ:** モデルコンテキストの更新に使用する前に、データをサニタイズします。 * **レート制限:** DoS攻撃を防ぐために、レート制限を実装します。 * **アクセス制御リスト(ACL):** ACLを使用して、MCPサーバー上の特定のリソースへのアクセスを制限します。 必要な具体的なセキュリティ対策は、MCPの具体的な実装と使用方法によって異なります。リスクを慎重に評価し、適切なセキュリティ制御を実装することが重要です。
LinkedIn Agent MCP
Enables AI assistants to connect to LinkedIn, accessing profiles and companies, searching for jobs and people, managing saved jobs, updating job-search profile settings, and inspecting analytics.
NoteBook MCP
Enables AI agents to query personal Google NotebookLM notebooks using a persistent browser session for instant queries without an official API.
Odybook MCP Server
Enables AI assistants to search tours, check availability, and manage bookings via Odybook's experience management platform.
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.
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.
fec-mcp-server
Query FEC campaign finance data — search candidates, track donations, analyze spending, and monitor Super PAC activity via the OpenFEC API.
Instahyre MCP
Provides MCP tools for job search, inbound recruiter activity triage, conversation inbox access, and guarded profile updates.
mcp-mbta
Enables real-time access to Boston MBTA transit data (subway, bus, commuter rail, etc.) via the MBTA v3 API.
Blender MCP
Enables AI assistants to control Blender 3D software through natural language, with tools for modeling, materials, animation, rendering, and rigging.
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.
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.
FusionSearch MCP
把五个搜索源熔进一个 MCP —— 一次调用,多源取证 · 交叉验证 · AI 汇总
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.
Law Office SQLite MCP Server
A Model Context Protocol server for law office database management that enables tracking clients, cases, billable time, and invoices.
Meta Kaggle MCP Server
Searches and retrieves information from Meta Kaggle dataset, including competitions, discussions, users, and forums, enabling data exploration and analysis through natural language queries.
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.
CloudVision MCP Server
Enables querying and interacting with Arista CloudVision via MCP, supporting both HTTP and gRPC connections.
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.
brazil-pncp
Provides access to Brazilian government procurement (PNCP) data without API keys, enabling natural language queries through Pipeworx's AI gateway.
Kimi Partner
Enables Codex to delegate scoped frontend implementation tasks to Kimi, while Codex retains task planning, review, and acceptance.
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.
kubernetes-runbooks-mcp-server
Provides access to Kubernetes troubleshooting runbooks, enabling search, discovery, and retrieval of guides for common issues like pod crashes, node problems, and network failures.
Calculator MCP Server
A unified mathematical calculator that automatically detects expression types and performs basic arithmetic, statistical calculations, equation solving, and batch computations with 20+ built-in mathematical functions.
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.
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.
QuantumArchitect MCP
Enables AI agents to create, validate, evaluate, and score quantum circuits with support for multiple hardware platforms. Provides tools for generating quantum algorithms (Bell states, Grover's, VQE), simulating circuits, checking hardware compatibility, and assessing circuit quality metrics.