Browse the catalog

Persistent memory layer for AI coding agents — current-state retrieval that knows what is still true. Claude Code, Codex, Gemini CLI.

A minimal, production-ready MCP server running on AWS Lambda with Streamable HTTP transport, enabling deployment of custom tools behind API Gateway.

Give AI agents access to Formester form submissions. Read individual responses, search and filter across forms, write AI-generated insights back as custom fields, and process file attachments including PDFs and images.

MCP server that integrates with multiple Google services, providing Claude with over 50 tools for managing tasks, contacts, calendar, Gmail, documents, spreadsheets, presentations, chat, and meetings.

A modular production-ready system that provides specialized agents for math, research, weather, and summarization tasks through a unified MCP toolbox with smart supervisor capabilities.

Codabench drives the full ML benchmark participant workflow through the Codabench REST API. It enables AI assistants to manage competition submissions, retrieve leaderboard results, and interact with benchmark datasets on the Codabench platform. The server requires a Codabench API token for authentication.

Deterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.

Provides VC-grade startup intelligence, allowing founders to validate ideas and VCs to screen deals using tools like scoring, investor matching, and financial analysis.

Enables AI assistants to interact with Dynamics 365 Commerce systems through 125+ tools covering customer management, sales orders, cart operations, product searches, inventory tracking, and store operations. Provides comprehensive mock data for development and testing purposes.

MCP server for handling ADR Agreement provisions for AI models / Serwer MCP do obsługi przepisów Umowy ADR dla modeli AI

Fetches MetService CAP Atom feed for weather alerts and exposes tools to get active road warnings and all alerts.

Enables management of TuxCare ePortal resources such as servers, feeds, registration keys, patchsets, and users through the ePortal API, with support for basic and API key authentication.

This MCP server, developed by Hannes Rudolph, enables AI assistants to query and analyze iMessage conversations on macOS. Built with FastMCP and the imessagedb library, it provides read-only access to the iMessage database with robust safety features like phone number validation and attachment handling. The server exposes a 'get_chat_transcript' tool that retrieves message history for specific contacts, including text, timestamps, and attachment info. By connecting AI capabilities with personal messaging data, this implementation allows AI systems to gain insights from conversation history while maintaining privacy and security. It is particularly useful for personal productivity use cases like summarizing past discussions, analyzing communication patterns, or extracting action items from chats.

Provides PostgreSQL database management and analysis via MCP, enabling schema exploration, query execution, performance monitoring, and database health checks.

Enables Claude to interact with hledger for financial analysis, including account balances, transactions, and financial statements.

Enables Claude to design system architectures and scaffold minimal Python/Docker implementations, with live D3 visualization in the browser.

Enables database schema inspection, Yii2 console command execution, and project management tools for Yii2 framework via Claude Code.

Provides macroeconomic data (GDP, inflation, unemployment, trade) for any country via MCP tools, sourced from World Bank and US BLS, no API keys required.

This MCP server provides a bridge between AI agents and the Bazel build system, enabling interaction with Bazel workspaces through a standardized protocol. It implements six tools for building targets, querying dependencies, running tests, listing available targets, fetching external dependencies, and changing workspace paths at runtime. The server includes robust security features to prevent command injection, supports multiple configuration methods (CLI arguments, environment variables, and config files), and is designed to work seamlessly with Cursor and Claude Desktop, making it particularly useful when AI environments have misconfigured shells that prevent direct Bazel usage.