Browse the catalog

AI video generation MCP server for ChatGPT, Claude, Cursor and Antigravity. Seedance 2 Mini, Seedance 2, Kling 2.6 and Grok Imagine behind one OAuth endpoint, with the cost of each returned before generating.

Enables incremental editing of XMind mind maps using atomic tools for reading, creating, and surgically editing .xmind files.

MCP server for Bing Webmaster Tools. Search performance, crawl health, backlinks and indexing from Claude and other AI assistants. Runs on Cloudflare Workers.

The JSON MCP Server provides tools for efficient JSON file manipulation, allowing AI assistants to split large JSON files into smaller chunks and merge multiple JSON files into a single consolidated file. Developed by Vadym Nastoiashchyi, this TypeScript implementation uses the Model Context Protocol SDK to expose two primary tools: 'split' for dividing JSON arrays into specified sizes while preventing excessive fragmentation, and 'merge' for combining multiple JSON files from a directory into a single output file. The server includes robust path validation, home directory expansion, and error handling to ensure reliable operation across different environments. It's particularly valuable for data processing workflows that involve large JSON datasets that need to be broken down for processing or consolidated for analysis.

Flag AI tells, weasel words, passive voice, duplicate words, long sentences, nominalizations, hedging, and filler adverbs

Enables searching, reading, and managing a Calibre ebook library through natural language, with features like metadata search, full-text search, content extraction, and library management.

A deployment template for hosting remote Model Context Protocol servers on Cloudflare Workers using Server-Sent Events (SSE). It enables developers to expose custom tools to MCP-compatible clients like Claude Desktop and Cloudflare AI Playground without requiring authentication.

An MCP server that provides a guarded interface to the mem9 persistent memory backend, protecting AI agents against prompt injection, secret leakage, and memory poisoning.

Enables AI assistants to query and analyze AI agent sessions from observability providers like Shepherd (AIOBS) and Langfuse, allowing users to debug agent runs, compare sessions, track performance, and analyze LLM usage patterns.

A local-first MCP safety layer that blocks dangerous files and redacts secrets before AI agents can access them, ensuring safe vibe coding.

Generates customizable test/placeholder images as PNG files with specified dimensions (1-4096px), hex colors, and optional labels. Automatically creates directories and adds dimension overlays with smart contrast text.

A minimal Python-based proxy that bridges local MCP STDIO clients with remote MCP SSE servers. It enables bidirectional JSON-RPC message passing between standard command-line tools and web-based remote endpoints.

Complete Windows setup guide for chrome-devtools-mcp with Codex, Cursor, Windsurf, VS Code extensions, and other AI coding assistants. Includes PowerShell scripts, configuration examples, and troubleshooting for Windows 10/11.

Provides safe filesystem access for AI clients with root confinement, read-only mode, and file operations like read, write, search, copy, move, delete.

Enables read-only SMART on FHIR R4 discovery, search, and read operations against public synthetic sandboxes, returning actual empty results and 404s rather than inventing patient data.

Learning and experimenting with the Model Context Protocol by building practical MCP servers and integrations.

This Node.js implementation of a Git repository browser leverages the Model Context Protocol (MCP) to provide efficient and deterministic access to remote Git repositories. Developed by Razorback16, it offers two main tools: one for retrieving a tree-like representation of a repository's directory structure, and another for reading the contents of specified files. The server utilizes native Node.js modules, fs-extra for enhanced file operations, and simple-git for Git repository interactions. It implements clean error handling, resource cleanup, and creates deterministic temporary directories based on repository URL hashes. This implementation is particularly useful for AI assistants or applications that need to analyze or interact with Git repositories programmatically, without requiring local clones.

Provides AI assistants direct access to SEC EDGAR filing data — financials, filings, and filing text — with no API key required.

Model Context Protocol (MCP) server on Java 21: virtual threads, blocking I/O, STDIO