Browse the catalog

Enables integration with iFlytek's SparkAgent Platform to invoke task chains and upload files. Provides tools for interacting with iFlytek's AI agent services through the Model Context Protocol.

A learning project that wraps a FastAPI app with endpoints for random facts and Japan FAQs as MCP tools, enabling LLMs to call them via LiteLLM proxy.

Enables AI applications to manage JIRA issues, workflows, and tasks through a standardized MCP interface, facilitating real-time updates and seamless interaction with JIRA's API.

This knowledge graph MCP server, developed by Anthropic, enables persistent memory for AI assistants through a local graph database. It provides tools for creating, querying, and manipulating entities and relationships, allowing assistants to build and maintain structured knowledge about users and contexts across conversations. The implementation uses TypeScript and file-based storage, with a customizable memory path for flexibility. It's designed for enhancing AI personalization and context retention in applications like chatbots, virtual assistants, or any scenario requiring long-term information persistence and retrieval in natural language interactions.

NHL API server that provides a comprehensive bridge to official NHL web and stats APIs, enabling retrieval of real-time sports data including team standings, player statistics, game schedules, and roster information. Built with TypeScript and the MCP SDK, it offers a flexible, multi-endpoint approach to fetching NHL data with robust error handling and fallback mechanisms for API reliability.

MCP server exposing tweetfeed.live's IOC feed (URLs, domains, IPs, hashes) as tools for querying threat intelligence, with checks, enrichment, trends, and campaign clustering.

A demo MCP server for MongoDB built using Embabel. It showcases how AI agents can interact with MongoDB through the Model Context Protocol, enabling operations such as listing databases, fetching collections, executing simple and complex queries, managing indexes, creating collections, and inserting documents

This Discord webhook MCP server, developed by genm, enables seamless integration between AI agents and Discord channels. Built with TypeScript and leveraging the Model Context Protocol SDK, it provides a straightforward way to send messages, including custom usernames and avatars, to Discord webhooks. The implementation focuses on simplicity and ease of use, offering a command-line interface for quick setup and deployment. It's particularly useful for developers and teams looking to incorporate AI-generated content or notifications into their Discord workflows, enabling use cases such as automated updates, AI-assisted moderation, or interactive chatbots without dealing directly with Discord's API complexities.

AI-powered design and management for Webflow Sites

Enables Claude to read and query SAP SQL Anywhere databases using natural language, with read-only access and SQL query generation.

An MCP server that searches official FEC PDF rulebooks for compliance and contribution limits, and provides real-time lookups against the OpenFEC API for candidates, committees, filings, and financial data.

Java profiling MCP via jcmd/jfr/jps. Diagnose performance, analyze threads, inspect JFR recordings.

This MCP server for LinkedIn, developed by Hritik Raj, enables AI agents to interact with LinkedIn's platform for job applications and feed searching. Built using Python and leveraging the unofficial LinkedIn API, it provides tools for profile retrieval, advanced job searching, feed post retrieval, and resume analysis. The implementation focuses on simplifying LinkedIn interactions, offering functionality to extract key profile information, perform customizable job searches, and parse resumes in PDF format. It's particularly useful for applications requiring automated LinkedIn engagement, enabling use cases such as job matching, content curation, and candidate screening without directly dealing with LinkedIn's API complexities.

Open-source Windows MCP server for AI assistants. File, clipboard, screenshot, process & power mgmt.

Enables AI agents to interact with a double-entry ledger, offering tools for account management, balanced journal entries, balance queries, trial balance, and penny-perfect allocation. Built with safety by construction: no update/delete tools, idempotent posting, and an append-only journal.

Enables AI assistants to directly operate Bilibili, providing 27 tools for login, search, content publishing, data analysis, and interaction.

Enables users to compare and get recommendations across multiple supermarket products, combining curated specifications with realtime price and review lookups.

学習プランを自由に作成し、自分のペースで進める対話型学習MCPサーバー

Подключает личный аккаунт Telegram к ChatGPT

Human-MCP is a joke MCP server that puts a real human in the loop to respond to AI assistant requests via a Streamlit UI. The implementation creates a server that exposes tools and resources to AI assistants, but instead of automated responses, it routes all requests to a human operator through a simple web interface. This allows for creative, unpredictable, or humorous interactions where the AI believes it's communicating with an automated system while actually interacting with a person who can provide custom responses to each request.