Browse the catalog

Enables updating existing Google Drive files in place via Claude, preserving file ID, link, and revision history.

Enables AI assistants to interact with FreshRSS feeds via the Fever API, allowing listing feeds, fetching unread items, marking items as read/unread, and managing feed subscriptions.

62 semantic C#/.NET analysis tools via Roslyn: navigation, refactoring, code generation.

A production-ready MCP server for task management, enabling LLMs to create, list, and manage tasks via tools and resources, with support for local stdio and cloud Streamable HTTP deployment.

MCP server wrapping the Korean Film Council (KOFIC) Box Office API, enabling retrieval of daily/weekly box office data, movie search, and detailed movie information for use with Claude via a custom connector.

n8n MCP — query your own n8n instance (BYO).

Northeast Deal Intel connects AI assistants to its commercial real estate intelligence platform, providing access to deal flow data, property records, and transaction history for the Northeast United States. It exposes search and query tools for finding active deals, recent transactions, and market data. The service requires a subscription and API key for access.

Pay-per-call MCP server for WebberSites x402 Data API, offering 45 tools for AI agents: web scraping, document extraction, SEO audits, linting, crypto data, and more, with payment via USDC on Base.

Enables MCP-compatible clients to interact with Slack through Web API tools and subscribe to inbound Slack messages via Socket Mode notifications.

A portable MCP server that provides a shared persistent working state for AI coding agents, managing tasks, plans, notepads, memory, and project rules across different tools like Claude Code, OpenCode, and Cursor.

Manages FreeScout helpdesk tickets by fetching, analyzing, and updating tickets, drafting replies, and searching with advanced filters via the Model Context Protocol.

AEMPS CIMA — the Spanish Agency for Medicines and Health Products' public

Guardrails for AI agents on your cluster: a local, policy-gated Kubernetes MCP server with RBAC-style, context-scoped access control. Point it at an over-privileged kubeconfig — it still can't nuke prod.

MCP GitHub Server provides a comprehensive interface to the GitHub API, enabling AI assistants to perform repository operations, file management, issue tracking, and code search directly within conversations. Developed by MissionSquad (based on Anthropic's original implementation), this server supports dynamic GitHub Personal Access Token handling per request, allowing for flexible authentication while maintaining backward compatibility with environment variables. The implementation exposes over 30 tools covering everything from creating repositories and branches to managing pull requests and releases, making it particularly valuable for developers who need to interact with GitHub without context switching.

Enables LLMs to analyze Linux perf data files using 26 perf analysis commands, including report, script, annotate, and more, through typed tool parameters.

Live trend data for your AI. 25+ platforms. One connection.

Enables AI agents to send transactional emails through Quolle, including sending, batching, canceling, and checking delivery status of emails.

Enables users to retrieve GitLab commit records and automatically generate daily work reports that can be sent to WeChat Work groups. Supports querying commits by date and user, with seamless enterprise messaging integration.

DeepL MCP Server provides high-quality text translation capabilities by interfacing with the DeepL API. This TypeScript implementation exposes two main tools: 'translate_text' for translating strings between supported languages, and 'list_languages' for retrieving available language options. The server handles API authentication, request validation using Zod schemas, and comprehensive error handling for various failure scenarios. It's particularly useful for AI assistants that need to perform accurate translations across multiple languages without requiring users to interact directly with the DeepL API.