Browse the catalog

Delve MCP server provides a complete interface to the Delve debugger for Go programs through the Model Context Protocol. It implements all major debugging capabilities including starting debug sessions, setting breakpoints, controlling execution flow, and inspecting program state. The server exposes Delve's functionality as discoverable tools that can be executed by AI assistants, supporting various debug modes (debug, attach, exec, test), core dump analysis, and program tracing. Built with TypeScript using the MCP SDK, it requires Go with Delve installed and optionally Mozilla rr for replay debugging.

MCP server enabling agents to debug HTTP requests better (using powhttp)

Enables task management through natural language: create tasks, list and filter them, and update their status. It uses SQLite for persistence and supports both local stdio and remote SSE transports.

Enables AI agents to understand, query, and manipulate Honeybee building energy models through natural language via the Model Context Protocol.

An MCP server that provides an antidetect browser with persistent profiles, proxy support, and page control tools (16 tools) for agents, enabling identity-stable browsing sessions across runs.

This MCP server provides read-only access to OKX cryptocurrency exchange account data through five specialized tools for portfolio management and trading analytics, built by Max Barinov using TypeScript with the xmcp framework and okx-api client library. The implementation offers secure API integration requiring OKX credentials to retrieve account portfolios with USDT valuations, open orders, order history with date filtering, derivative positions, and aggregated account summaries including asset allocation breakdowns. Designed for traders and portfolio managers who need programmatic access to their OKX trading data for analysis, reporting, and integration with AI assistants for cryptocurrency portfolio monitoring and trading decision support.

Exposes Futurepedia AI tool crawling and universal web page parsing as MCP tools for assistants.

Slack MCP Server — send messages, manage channels, search, react, upload files, and manage users via Slack Web API, tailored for ADK-Rust Enterprise.

BookBrainz MCP — open book metadata (MetaBrainz / sister of MusicBrainz)

A production-ready MCP server for the Hevy fitness API that exposes 27 tools for reading, writing, and analyzing workout data, enabling LLM-driven personal trainer workflows.

Provides an MCP server exposing compute, verify, and plot tools backed by Giac/Xcas for exact symbolic and numerical mathematics, enabling LLMs to solve calculus, algebra, geometry, and more with verified results.

Enables AI assistants to answer questions about Finnish social benefits (Kela) by providing tools for searching, checking eligibility, and getting application steps.

An MCP server demo for retrieving Market information

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

Enables AI agents to use Mint as a safety layer for file operations on macOS, providing storage growth analysis, cleanup suggestions, and journaled, reversible deletions via MCP tools.

Enables read-only assessment of AWS environments by inventorying resources, running security and operational checks, and generating actionable reports with cost analysis. Designed for contractors with support for assume-role authentication using external IDs.

Enables interaction with N-able Passportal Documents API via MCP, allowing users to list and manage documents using natural language.

MCP server to read and write events on chouseisan.com (Chouseisan), a Japanese scheduling tool, using unofficial HTTP protocol. Enables creating events, fetching schedules, and managing responses via AI agents or CLI.

This MySQL MCP implementation, developed using Python, provides a standardized interface for interacting with MySQL databases through the Model Context Protocol. It utilizes the mysql-connector-python library to offer MySQL functionality, enabling operations like data querying, insertion, and manipulation. The implementation is containerized using Docker for easy deployment and scalability. By abstracting MySQL interactions into an MCP interface, it allows AI systems to seamlessly work with relational database data and operations. This server is particularly useful for applications requiring structured data storage and retrieval, such as content management systems, user authentication services, or data-driven web applications.

Docs for the ClimbPast MCP server: read and edit GA4, Search Console and Google Tag Manager from Claude, ChatGPT, Cursor or any MCP client