Browse the catalog

MCP server for PostgreSQL, providing schema discovery, catalog introspection, read-only querying, and optional safe write operations to AI assistants.

Enables natural-language querying of historical NBA game data from a read-only SQLite database.

42 developer tools through one MCP install

Enables web search capabilities using DuckDuckGo's free API without requiring authentication or API keys.

Robust, production tested MCP Server for linear (API)

MCP server exposing Profilarr's v1 REST API as tools, enabling an LLM to inspect and manage linked databases, connected Radarr/Sonarr instances, backups, jobs, announcements, and system status.

Cloudbet Sports Data MCP Server

This MCP server provides access to Hacker News data through a set of capabilities including searching stories and comments, retrieving various types of stories, fetching individual stories with comments, and accessing user profiles and submissions. Developed by devabdultech, it integrates with the Hacker News API and is built using TypeScript and Node.js. The server is designed for use cases requiring real-time access to Hacker News content, such as news aggregation, trend analysis, or building custom Hacker News clients.

GPT-5 MCP server that provides direct integration with OpenAI's GPT-5 API through the new Responses endpoint, offering two core tools for text generation: gpt5_generate for simple prompt-based requests and gpt5_messages for structured conversation handling with message roles. The implementation uses safe property access patterns to handle API response parsing and excludes unsupported parameters like temperature and max_tokens, making it valuable for developers who want to access GPT-5's capabilities through MCP-compatible applications without building their own OpenAI API integration layer.

A read-only MCP server for discovering engineering work and reusable assets on Archimedes Market. It enables searching and retrieving public assets and bounties through natural language.

Exposes a provenance-aware knowledge graph to AI agents over MCP, providing tools like get_fact and search_documents that return precise answers with source citations.

MCP server for Microsoft SQL Server — schema discovery, profiling, safe writes, and DDL

A Model Context Protocol server that gives Claude (or any MCP-compatible LLM) direct access to a self-hosted WordPress site over its REST API.

Bilibili MCP Server provides a simple interface to the Bilibili API, enabling search functionality across the popular Chinese video platform. Built with FastMCP, it exposes a single tool that allows querying the Bilibili search API with optional authentication via session data cookies. The implementation is lightweight, requiring only Python 3.12 and minimal dependencies (mcp[cli] and requests), making it ideal for workflows that need to retrieve video content, user information, or other searchable data from Bilibili without leaving the conversation interface.

An MCP server that enables AI assistants to interact with Freshservice service desk, supporting ticket search, retrieval, and creation via a configurable, Docker-first deployment.

A FastMCP server for GitLab 16.x that enables project, MR, pipeline, and commit queries, bugfix contribution summaries, release notes drafts, and comprehensive Runner management.

A tiny MCP server that can read and write in database interacting with LLM

Enables AI clients to search for academic papers, fetch metadata by DOI, retrieve open access PDF links, and extract full text from research papers using the Unpaywall API. Provides seamless access to scholarly literature for research and analysis tasks.

Tasker MCP server by Luis Sanchez that bridges AI assistants with Android's Tasker automation platform through HTTP API integration, enabling conversational control of device automation tasks, smart home routines, and custom workflows. The implementation includes a CLI server with both stdio and SSE transport modes, a utility for converting Tasker XML exports into MCP tool definitions, and support for dynamic argument parsing from Tasker task variables with proper type inference and validation. Built with Go and designed for Android power users, it transforms Tasker's extensive automation capabilities into AI-accessible tools, making it valuable for voice-controlled home automation, contextual device management, and integrating physical world actions into AI workflows through Tasker's deep Android system integration.

Enables LLM clients to run Akamai edge diagnostics (DNS, MTR, curl, error analysis, etc.) and manage support cases via the Model Context Protocol.