MCP (Model Context Protocol) servers let AI agents reach beyond the codebase. They connect your agent to external APIs, databases, search engines, and services through a standardized protocol — so the agent can actually take action, not just write code.
1046 servers
13 production-ready tools for AI agents — one API key, zero complexity. Docs · Playground · OpenAPI Spec · npm Building AI agents that interact with the real world? You'd normally need: No credit card. No setup. 13 endpoints ready to use. Use Agent Toolbox as an MCP server in Claude Desktop, Cursor, or Windsurf: Add to Claude Desktop config: See MCP Quickstart Guide for full setup instructions. Al
MCP skill for airtable. Provides 8 tools: ping, list_bases, search_bases, list_tables_for_base, get_table_schema, list_records_for_table, create_records_for_table, update_records_for_table
Model Context Protocol server for OriginSelect — search ethical, origin-verified products and brands via AI agents. Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client. No install needed — just add to your Claude Desktop config: Then add to Claude Desktop config: Add to your MCP settings: Once connected, ask your AI assistant: - "Find organic baby products from Canada under
AiyoPerps is a perpetual futures desktop terminal that supports both CEX (centralized) and DEX (decentralized) trading. It provides a full desktop UI, an MCP server for AI agents, and a local REST API. With AiyoPerps, you can trade crypto perpetual futures manually, with AI collaboration, or fully driven by AI. If you think this project is cool, feel free to buy us a coffee! When you sponsor us, y
- Fixed reply threading — auto-resolves In-Reply-To and References headers so email replies land in the correct thread instead of creating orphaned messages (upstream PR 91, still pending) - Send-as alias support — optional from parameter for multi-identity email management (send from any configured Gmail alias) - Reply-all tool — replyall automatically fetches the original email, builds To/CC rec
Self-hosted meeting intelligence platform bots • real-time transcription • storage • API • user interface Google Meet • Microsoft Teams • What’s new • Quickstart • Vexa is an open-source, self-hostable API for real-time meeting transcription. It automatically joins
A feedback loop for people building AI skills and MCP servers. You're building a skill, an MCP server, or a custom prompt strategy that's supposed to make an AI coding assistant better at a specific job. But how do you know it actually works? How do you know your latest commit made things better and not worse? Pitlane gives you the answer. Define the tasks your skill should help with, set up a bas
Instead of manually writing a system prompt, this tool mines your actual conversation history — your word patterns, recurring topics, and habits of thought — and distils them into a ~3k character profile that meaningfully changes how an AI responds to you. The pipeline runs entirely locally. It never sends your conversation data anywhere. 1. Stream conversations-.json using ijson — never loads the
An MCP (Model Context Protocol) server that connects AI agents like Cursor and Claude Code to your ElmapiCMS instance. Manage collections, fields, content entries, and assets programmatically through natural language. Or install locally: The server requires three environment variables: Add this to your Cursor MCP settings (~/.cursor/mcp.json): Add the MCP server using the Claude Code CLI: If your
A personal filesystem that works as your life operating system — designed to be read, queried, and operated on by an AI agent. Life OS is a structured set of markdown files that give an AI agent (Goose, Claude, or any LLM with filesystem access via MCP) persistent context about your life — who you are, what you're working on, what you're learning, and what's happened. The AI reads these files at t
A Model Context Protocol (MCP) server for the Discord API (JDA), allowing seamless integration of Discord Bot with MCP-compatible applications like Claude Desktop. Enable your AI assistants to seamlessly interact with Discord. Manage channels, send messages, and retrieve server information effortlessly. Enhance your Discord experience with powerful automation capabilities. Manual Installation M
한국어 | English 1969년 Ken Thompson이 Unix를 만들 때, 그는 출력 대상이 사람이라고 가정했다. 정확히 말하면 터미널 앞에 앉아 있는, 눈이 달린 생물. 반세기가 지났다. 이제 터미널을 읽는 것은 사람만이 아니다. AI 에이전트는 ls -la를 실행하고, 그 출력을 받는다. 그리고 거기서 진짜 작업이 시작된다. 공백을 기준으로 분리하고, 첫 번째 열이 권한이고, 세 번째가 소유자이고, 파일명이 어디서 시작하는지를 토큰을 태워가며 추론한다. 인간의 눈이 0.1초에 처리하는 것을. 이것은 번역이 아니다. 암호화된 적도 없는 메시지를 해독하는 일이다. 세 번의 번역이 일어난다. 첫 번째: 커널이 파일시스템 메타데이터를 stat 구조체로 관리한다. inode, mode, uid, gid,
Every multi-step tool workflow burns an LLM round-trip per step. The agent calls tool A, waits, sends the full context back to the model, gets a decision to call tool B, calls it, sends everything back again. Each round-trip re-transmits 2K–10K tokens on what is essentially plumbing. For a session with 20 two-step workflows, that's 20 wasted model calls, ~100K wasted tokens, and 20–40 seconds of a
A Model Context Protocol (MCP) server that provides intelligent search capabilities for discovering relevant Claude Agent Skills using vector embeddings and semantic similarity. This server implements the same progressive disclosure architecture that Anthropic describes in their Agent Skills engineering blog, making specialized skills available to any MCP-compatible AI application. An open-source
Real-time global intelligence across 30+ domains with 109 MCP tools, a live ops-center dashboard, a CLI, and a Qdrant vector store for enterprise-grade semantic search across accumulated intelligence. All data comes from free, public APIs — no paid subscriptions required. Built for AI agents that need world awareness: market conditions, geopolitical risk, military posture, supply chain disruptions
A Model Context Protocol (MCP) server that provides SQL analysis, linting, and dialect conversion capabilities using SQLGlot. The SQL Analyzer MCP server provides tools for analyzing and working with SQL queries. It helps with: - SQL syntax validation and linting - Converting queries between different SQL dialects (e.g., MySQL to PostgreSQL) - Extracting and analyzing table references and dependen
A Model Context Protocol (MCP) server implementation for running k6 load tests. - Simple integration with Model Context Protocol framework - Support for custom test durations and virtual users (VUs) - Easy-to-use API for running k6 load tests - Configurable through environment variables - Real-time test execution output Before you begin, ensure you have the following installed: - Python 3.12 or hi
An MCP server that enables AI agents to control web browsers using browser-use. - uv - Fast Python package manager - Playwright - Browser automation - mcp-proxy - Required for stdio mode Create a .env file: - [x] Browser Automation: Control browsers through AI agents - [x] Dual Transport: Support for both SSE and stdio protocols - [x] VNC Streaming: Watch browser automation in real-time - [x] Asyn
MCP (Model Context Protocol) server that exposes TestCollab test management functionality to AI assistants like Claude. - Test Case Management - listtestcases - List test cases with filtering, sorting, and pagination - gettestcase - Fetch a single test case with full details (including steps) - createtestcase - Create test cases with steps and custom fields - updatetestcase - Update existing test
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models. This package provides MCP interface into Playwright. If you are using a coding agent, you might benefit from using the CLI+SKILLS instead. -
- A minimal server/client application implementation utilizing the Model Context Protocol (MCP) and Azure OpenAI. 1. The MCP server is built with FastMCP. 2. Playwright is an an open source, end to end testing framework by Microsoft for testing your modern web applications. 3. The MCP response about tools will be converted to the OpenAI function calling format. 4. The bridge that converts the MCP
A Model Context Protocol server for the QA Sphere test management system. This integration enables Large Language Models (LLMs) to interact directly with QA Sphere test cases, allowing you to discover, summarize, and chat about test cases. In AI-powered IDEs that support MCP, you can reference specific QA Sphere test cases within your development workflow. - Node.js (recent LTS versions) - QA Sphe
A powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously. - Parallel Searching: Supports searching with multiple keywords on Google simultaneously, improving search efficiency - Browser Optimization: Opens multiple tabs in a single browser instance for efficient parallel searching - Automatic Verification Handling: Intelligently detects CAPTCHA
mcp-name: io.github.wmarceau/hvac-quotes HVAC equipment RFQ (Request for Quote) management via MCP for Claude Desktop. - Submit RFQs to HVAC equipment distributors - Check RFQ status and track responses - Get and compare quotes from multiple distributors - Simulate quotes for testing workflows Add to your claudedesktopconfig.json: Submit a Request for Quote to HVAC distributors. Check the status o