AI MCP Servers
MCP servers extend what AI models can do by providing structured access to external tools, APIs, and data sources. Google Calendar, GitHub, Slack, databases — any service can become an MCP tool.
AWS Labs' official MCP suite — docs, CDK, Bedrock KB, cost, Lambda and more as agent tools.
Zapier's hosted MCP — 8,000+ app integrations exposed as allowlisted agent tools.
Official Hugging Face MCP — search models/datasets/Spaces/papers and call Spaces as tools.
Atlassian's official hosted MCP — Jira + Confluence with OAuth, permission-bounded agent access.
Official MCP reference server — current time and timezone conversion tools for agents.
Official E2B MCP — secure cloud-sandbox code execution (Python/JS) as an agent tool.
Official ClickHouse MCP — read-only SQL analytics over ClickHouse and chDB for agents.
Official Chroma MCP — vector + full-text retrieval and collection management as agent tools.
Official Apify MCP — 6,000+ scrapers/automations (Actors) callable as agent tools.
Official MCP test server exercising every protocol feature — the compatibility target for client developers.
Claude API — Opus/Sonnet/Haiku, 200K context, tool use, computer use, prompt caching.
AI-optimized web search and content extraction via Tavily MCP.
Query and manage MongoDB databases and collections via MCP.
Scrape websites and extract structured data via Firecrawl MCP.
Neural web search and content retrieval via Exa MCP.
Search, index, and query Elasticsearch clusters via MCP.
Extract and analyze YouTube video transcripts via MCP.
Create, query, and analyze SQLite databases via MCP.
Automate browser interactions and take screenshots via Puppeteer MCP.
Query and explore PostgreSQL databases through MCP tools.
Automate browsers and run web tests via Playwright MCP.
Search, read, and manage Google Drive files via MCP.
Manage Firebase Firestore, Auth, and Storage via MCP.
Manage Vercel deployments, projects, and domains via MCP.
Create and manage Todoist tasks and projects via MCP.
Send messages and manage Telegram chats and bots via MCP.
Manage Supabase databases, auth, and storage via MCP.
Manage Stripe payments, customers, and subscriptions via MCP.
Manage Redis keys, caches, and data structures via MCP.
Query databases and manage schemas via Prisma MCP.
Manage Pinecone vector indexes and similarity searches via MCP.
Search, read, and write Obsidian vault notes via MCP.
Search, read, and edit Notion pages and databases via MCP.
Manage Neon serverless Postgres databases and branches via MCP.
Create and manage Linear issues and projects via MCP.
Manage Kubernetes clusters, pods, and deployments via MCP.
Search, create, and manage Jira issues and sprints via MCP.
Manage HubSpot CRM contacts, deals, and marketing via MCP.
Control smart home devices and automations via Home Assistant MCP.
Query Grafana dashboards, datasources, and alerts via MCP.
Create, search, and manage Google Calendar events via MCP.
Manage GitLab repos, merge requests, and CI/CD pipelines via MCP.
Interact with GitHub repositories, issues, and pull requests via MCP.
Manage local Git repositories, commits, and branches via MCP.
Read, write, and manage local filesystem resources via MCP.
Read Figma designs, components, and design tokens via MCP.
Manage Docker containers, images, and volumes via MCP.
Query Datadog metrics, logs, and monitors via MCP.
Search, read, and create Confluence wiki pages via MCP.
Manage Cloudflare Workers, KV, R2, and DNS via MCP.
Run cloud browser sessions and web automation via Browserbase MCP.
Search the web using Brave Search API through MCP.
Create and manage Asana tasks, projects, and workspaces via MCP.
Search and read arXiv academic papers and abstracts via MCP.
Read and send Slack messages and manage channels via MCP.
Manage Shopify stores, products, and orders via MCP.
Enable structured step-by-step reasoning and thought revision via MCP.
Query Sentry issues, errors, and stack traces via MCP.
Manage PagerDuty incidents, alerts, and on-call schedules via MCP.
Persistent knowledge graph memory storage for LLM conversations.
Access Google Maps geocoding, directions, and place data via MCP.
Fetch and convert web pages to markdown for LLM processing.
Search the web privately via DuckDuckGo MCP.
Read and send Discord messages and manage servers via MCP.
Post, search, and interact on Bluesky social network via MCP.
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Pre
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workfl
The cultural GPS for AI commerce. 504,472 aesthetic worlds mapped across 193 dimensions — from dark academia to k-beauty to quiet luxury. 3,154 autonomous agents update intelligence every 48 hours. 9 tools: product recommendations with affiliate links, brand cultural position, trend intelligence, c
Your AI agent has two states. Ternlang gives it three. 30 tools — FREE, no key needed. The third state isn't null. I
Manage Gmail end-to-end: send, draft, reply, forward, and bulk-modify or delete messages and threads. Organize your inbox with labels, archiving, and trashing, and retrieve messages, attachments, and profile details on demand. Access and search contacts to autofill recipients and keep people data in
Enable your LLMs to perform accurate numerical calculations with a simple API. Leverage basic arithmetic and statistical functions to enhance your applications. Simplify complex mathematical tasks effortlessly and improve your model's capabilities.
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Verified knowledge base for AI Agents — certified Swiss facts, no hallucinations. Swiss Truth gives your AI agent access to a curated, expert-reviewed knowledge base — covering Swiss law, health, finance, education, energy, politics, climate, AI/ML, and world science. Every fact has passed a 5-s
Real-Time Flight Data Access Connect to liveflight pricing and availability. Access comprehensive flight data from multiple sources with live pricing updates. Multiple Search Types Find the most affordable flights between any airports. View flight prices across entire months for flexible travel p
Read, write, and format spreadsheet data. Manage sheets, run formulas, and collaborate on structured data in real time.
Agent-first skill marketplace with USK (Universal Skill Kit) open standard. Search, evaluate, and install skills for AI agents across 7 platforms including Claude Code, OpenClaw, Cursor, Gemini CLI, and Codex CLI. Agents discover skills via API with trust-level filtering (verified/community/sandbox)
CryptoIZ MCP v4.16.17 — AI-powered Solana DEX whale intelligence. 9 tools (7 paid + 2 free): whale alpha scanner, divergence (hidden/breakout/classic), accumulation/neutral/distribution phase scoring, BTC macro regime, BTC Futures signal. Pay per call with USDC via x402 Dexter — gas sponsored, no SO
Provide fast, privacy-friendly web and AI-powered search capabilities with integrated content and metadata extraction. Enhance your AI assistants by enabling comprehensive web scraping without requiring API keys. Optimize performance with caching and secure usage through rate limiting and user agent
Search the web in real time to get trustworthy, source-backed answers. Find the latest news and comprehensive results from the most relevant sources. Use natural language queries to quickly gather facts, citations, and context.
Provide AI agents and automation tools with contextual access to blockchain data including balances, tokens, NFTs, and contract metadata. Enable multi-chain support and deliver enhanced user experience with progress notifications for long-running queries. Facilitate seamless integration with AI host
Provide seamless access to open datasets and collections from data.gov.sg. Enable searching, metadata retrieval, and filtered dataset downloads for analysis.
Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic Scholar, and IACR. Fetch PDFs and extract full text to accelerate literature reviews. Get consistent metadata for easier filtering, citation, and analysis.
Model Context Protocol Servers
A collection of MCP servers.
Identity Intelligence for Agentic AI Workflows Connect Data. Power Intelligence.™ MCP Server v0.39.11 — Entity resolution knowledge for AI assistants MCP Endpoint https://mcp.senzing.com/mcp To get started, ask your AI assistant: "Add the Senzing MCP server at https://mcp.senzing.com/mcp" This is
Build interfaces that follow the Korea Responsive Design System (KRDS) faster. Search and insert official components, retrieve ready-to-use HTML, and explore color, spacing, and typography tokens. Validate your code for KRDS compliance and accessibility and get actionable improvement suggestions.
63 deterministic quant computation tools for AI agents. Black-Scholes, Greeks, exotic derivatives, portfolio optimization, Monte Carlo, risk metrics (VaR, Sharpe, drawdown), technical indicators, bond pricing, yield curves, crypto/DeFi (impermanent loss, liquidation, funding rates), macro/FX, and ti
Provide AI-powered real-time analysis and intelligence on NPM packages, including security, dependencies, performance, and quality metrics. Enable faster and safer package management decisions by integrating with Claude and Anthropic AI. Deliver comprehensive insights such as vulnerability scanning,
Lotus Wisdom is a contemplative reasoning tool inspired by the Lotus Sutra. It guides AI through structured wisdom journeys for complex problems where logic alone isn't enough. Flow through wisdom domains (skillful means, non-dual recognition, meta-cognitive), take meditative pauses, and track your
# NWO Robotics MCP Server Control real robots, IoT devices, and autonomous agent swarms through natural language — powered by the [NWO Robotics API](https://nwo.capital). --- ## What This Server Does This MCP server exposes the full NWO Robotics API as 64 ready-to-use tools. Any MCP-compatible A
Visit https://brave.com/search/api/ for a free API key. Search the web, local businesses, images, videos, and news with rich, structured results. Refine results by country, language, freshness, and SafeSearch to pinpoint what you need. Generate concise summaries of findings to grasp key points faste
Discover and filter Polymarket prediction markets and events by tags, volume, liquidity, and activity. Analyze individual markets with probabilities, market health, and recent trade insights to inform decisions. Track trends across categories to spot opportunities and compare sentiment over time.
🚀 The fast, Pythonic way to build MCP servers and clients.
🚀 The fast, Pythonic way to build MCP servers and clients.
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.
Provide access to Chinese stock market data including historical prices, real-time data, news, and financial statements. Retrieve comprehensive financial information for stocks with flexible parameters. Enhance your financial analysis and decision-making with up-to-date market insights.
Fetch up-to-date, version-specific documentation and code examples directly into your prompts. Enhance your coding experience by eliminating outdated information and hallucinated APIs. Simply add `use context7` to your questions for accurate and relevant answers.
Find and download academic papers from leading sources like arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic Scholar, CrossRef, and IACR. Get standardized results and fetch full-text PDFs when available. Accelerate literature reviews with deep search and effortless retrieval.
**Lightning-fast domain search directly in your AI workflow** Search domain availability, generate brandable alternatives, and validate bulk domain lists without leaving Claude, Cursor, or any other MCP-compatible environment. Powered by the same sub-10ms API infrastructure behind Instant Domain Se
MCP for public datasets OpenDOSM (Developed by Seah Boon Keong) What it delivers: - 163 curated datasets (Department of Statistics Malaysia + sources) - Programmatic tools: discover, query, get latest, correlation, ARIMA forecasts (with fallback) Benefits: Accessibility - Economists, analysts, and
What are AI MCP Servers?
MCP (Model Context Protocol) servers give AI models standardized access to external tools and data sources. Instead of building custom integrations for every AI application, MCP provides a universal protocol: any MCP client (Claude, Cursor, Zed) can connect to any MCP server (GitHub, Slack, databases, APIs). Think of it as USB-C for AI — one standard connector that works everywhere.
How to Choose
Evaluate MCP servers on four dimensions: tool coverage (what actions can it perform?), authentication (how does it handle API keys and permissions?), transport type (stdio for local, SSE/HTTP for remote), and maintenance status (is it actively updated?). For data sources, check read vs. write support. For API wrappers, check rate limit handling.
Key Capabilities to Evaluate
Common Patterns
Local process communication. The MCP server runs as a child process of the client. Best for desktop apps and local tools.
Remote server communication. The MCP server runs as a web service. Best for shared, always-on integrations.
Multiple MCP servers combined — e.g., GitHub MCP + Slack MCP + Database MCP give the model access to code, communication, and data.
The model subscribes to changes in MCP resources, enabling reactive workflows.
What to Watch Out For
Top Capabilities
Browse all →Analyzes selected code or entire files and generates natural language explanations of what the code does, how it works, and why certain patterns were chosen. The feature can produce documentation in multiple formats (docstrings, comments, markdown) and supports various documentation styles (JSDoc, Sphinx, etc.). Developers can request explanations at different levels of detail (high-level overview, line-by-line breakdown, architectural context) through the chat interface, with responses appearing as formatted text or code comments.
Cody utilizes a context-aware engine that analyzes the current file and project structure to provide relevant code completions. It integrates with the Visual Studio Code API to access the Abstract Syntax Tree (AST) of the code, allowing it to suggest completions that are semantically relevant to the context, rather than relying solely on keyword matching. This approach ensures that the suggestions are not only syntactically correct but also contextually appropriate, enhancing developer productivity.
Converts natural language prompts into executable full-stack web applications by invoking an AI agent that generates React/Next.js frontend code, Node.js backend logic, and database schemas. The agent runs code in-browser via WebContainers to validate syntax and functionality before deployment, iterating on the generated code based on execution feedback. Token consumption scales with project complexity (larger codebases consume more tokens per iteration), and the agent supports design system imports from Figma and GitHub to accelerate UI generation.
Provides six model variants (tiny, base, small, medium, large, turbo) with parameter counts ranging from 39M to 1550M, enabling developers to choose optimal speed-accuracy tradeoffs. Tiny model runs at ~10x speed with 1GB VRAM; large model runs at 1x speed with 10GB VRAM. English-only variants (tiny.en, base.en, small.en) provide higher English accuracy by removing multilingual capacity. Turbo model (809M params) offers 8x speedup over large with minimal accuracy loss but lacks translation support.
Translates non-English speech directly to English text by using a task-specific token in the TextDecoder that signals translation mode, bypassing the need for intermediate transcription-then-translation pipelines. The AudioEncoder processes mel spectrograms identically to transcription, but the decoder generates English tokens directly from audio embeddings, reducing latency and error propagation compared to cascaded systems.
Transcribes audio in 98 languages to text in the original language using a unified Transformer sequence-to-sequence architecture with a shared AudioEncoder that processes mel spectrograms into language-agnostic embeddings, then a TextDecoder that generates tokens autoregressively. The system handles variable-length audio by padding or trimming to 30-second segments and uses task-specific tokens to signal transcription mode, enabling a single model to handle multiple languages without language-specific branches.
Detects the spoken language in audio by processing mel spectrograms through the AudioEncoder and using a language classification head that outputs probability distributions over 98 supported languages. The model leverages 680K hours of multilingual training data to recognize language characteristics from acoustic features alone, without requiring transcription. Language detection occurs as a preliminary step in the transcription pipeline and can be called independently via the language detection task token.
W&B Personal tier (free) and Enterprise tier support self-hosted deployment via Docker, enabling on-premise installation for teams with data residency or security requirements. Self-hosted instances run independently from W&B cloud, with optional integration to W&B cloud for cross-instance features. Supports custom domain configuration, HTTPS, and integration with corporate identity providers (LDAP, SAML, OAuth).
Browse Other Types
Autonomous AI systems that act on your behalf
ModelsFoundation models, fine-tunes, and specialized AI models
RepositoriesOpen-source AI projects on GitHub
APIsProgrammatic endpoints for AI capabilities
ExtensionsBrowser and IDE extensions powered by AI
WorkflowsAutomation sequences and AI pipelines
View all 19 types →Frequently Asked Questions
What is the Model Context Protocol (MCP)?
MCP is an open protocol that standardizes how AI models connect to external tools and data sources. It defines a common interface for tools (functions the model can call), resources (data the model can reference), and prompts (templates for common tasks). Any MCP-compatible client can connect to any MCP server.
Which AI models support MCP?
Claude (via Claude Desktop and Claude Code), Cursor, Zed, Windsurf, and a growing number of AI applications support MCP. The protocol is open-source and maintained by Anthropic, with community implementations for other platforms.
How do I build an MCP server?
MCP servers can be built in any language. The official TypeScript and Python SDKs are the fastest path. A minimal server defines tools with input schemas and handler functions, then exposes them over stdio or HTTP transport. The MCP specification at modelcontextprotocol.io has the full reference.