{"type":"mcp_server","name":"servers","description":"This repository offers reference implementations for Model Context Protocol (MCP) servers, showcasing how to grant Large Language Models secure access to various tools and data sources using TypeScript and Python SDKs.","category":"AI","language":"JavaScript","stars":87758,"forks":2764,"owner":"modelcontextprotocol","github_url":"https://github.com/modelcontextprotocol/servers","homepage":"https://modelcontextprotocol.io","setup":"## Setup\nTypescript-based servers can be used directly with `npx` (e.g., `npx -y @modelcontextprotocol/server-memory`).\nPython-based servers can be used with [`uvx`](https://docs.astral.sh/uv/concepts/tools/) or [`pip`](https://pypi.org/project/pip/).\nInstall `uv` / `uvx` using [these](https://docs.astral.sh/uv/getting-started/installation/) instructions and `pip` using [these](https://pip.pypa.io/en/stable/installation/).\nExample for Python servers: `uvx mcp-server-git` or `pip install mcp-server-git; python -m mcp_server_git`.\nConfigure the server into an MCP client, such as Claude Desktop, by specifying the command and arguments in the `mcpServers` configuration.","tools":"## Available Tools\n\n1. AWS KB Retrieval (Retrieval from AWS Knowledge Base using Bedrock Agent Runtime)\n2. Brave Search (Web and local search using Brave's Search API)\n3. EverArt (AI image generation using various models)\n4. Everything (Reference / test server with prompts, resources, and tools)\n5. Fetch (Web content fetching and conversion for efficient LLM usage)\n6. Filesystem (Secure file operations with configurable access controls)\n7. Git (Tools to read, search, and manipulate Git repositories)\n8. GitHub (Repository management, file operations, and GitHub API integration)\n9. GitLab (GitLab API, enabling project management)\n10. Google Drive (File access and search capabilities for Google Drive)\n11. Google Maps (Location services, directions, and place details)\n12. Memory (Knowledge graph-based persistent memory system)\n13. PostgreSQL (Read-only database access with schema inspection)\n14. Puppeteer (Browser automation and web scraping)\n15. Redis (Interact with Redis key-value stores)\n16. Sentry (Retrieving and analyzing issues from Sentry.io)\n17. Sequential Thinking (Dynamic and reflective problem-solving through thought sequences)\n18. Slack (Channel management and messaging capabilities)\n19. Sqlite (Database interaction and business intelligence capabilities)\n20. Time (Time and timezone conversion capabilities)\n21. Third-Party Servers (Official Integrations and Community Servers)\n22. Frameworks (Tools that make it easier to build MCP servers or clients)\n23. Resources (Additional resources on MCP)","faq":null,"created_at":"2024-11-19T01:10:17+00:00","updated_at":"2025-07-07T15:54:54+00:00","source_url":"https://model-context-protocol.com/servers/model-context-protocol-mcp-servers","related_articles":[]}