Browse the catalog

A Python implementation of an MCP server that extracts webpage content, removes ads and non-essential elements, and transforms it into clean, LLM-optimized Markdown.

An MCP server that exposes PPSSPP — the PlayStation Portable emulator — to any MCP-compatible client (Claude Desktop, Claude Code, etc.) via PPSSPP's built-in WebSocket debugger interface. Read and write PSP memory, drive games with button input, capture screenshots, set CPU breakpoints, inspect MIPS Allegrex registers — all through a clean tool interface. No bridge plugin needed; PPSSPP's debugg

Jira MCP Server enables AI assistants to interact with Atlassian Jira through a set of specialized tools. Built by Samuel Rizzo, this TypeScript implementation provides capabilities for listing projects, retrieving issue details, searching issues by project and assignee, listing project members, and checking user assignments. The server authenticates with Jira's API using email and token credentials, handles request validation with Yup schemas, and formats responses in markdown for optimal readability. It's particularly valuable for teams who want to query and analyze their Jira projects and issues directly within AI assistant conversations without context switching to the Jira interface.

This MCP terminal server, developed by Nicholas Rinard, provides a secure interface for AI assistants to execute shell commands in a controlled environment. Built with TypeScript and leveraging the Model Context Protocol SDK, it offers robust security features including command whitelisting, timeout controls, and output size limits. The implementation focuses on safe command execution, making it easier for AI models to interact with system-level operations without compromising security. It's particularly useful for scenarios requiring controlled access to terminal functionality, such as automated system management, development workflows, or providing AI assistants with limited shell access, while maintaining strict security boundaries and resource controls.

MCP server that exposes 108+ omega-cli OSINT tools for reconnaissance, web analysis, threat intelligence, and reporting, enabling AI assistants to perform comprehensive open-source intelligence tasks.

Exposes 7 tools for AI model intelligence: model recommendation based on use case, prompt optimization, parameter comparison, pricing lookup, capability analysis, and model ranking. Supports 67+ generative AI models with built-in caching for performance. Compatible with Claude Desktop, Cursor, and Windsurf via npm package @promptibus/mcp.

Find email addresses for people at companies and verify email validity using the Hunter.io API.

Playwright JavaScript E2E automation framework for e-commerce workflows using POM, fixtures, Jenkins CI/CD, MCP and AI-assisted Playwright Agents.

An MCP server for XRP Ledger identity features including DIDs, credentials, multisig, and safe transaction workflows.

An MCP server that runs on Linux and gives an MCP agent (e.g. Claude Code) SSH access to a Windows machine — to build, test, run commands, transfer files, and drive long-running or interactive jobs.

Enables deployment of a remote MCP server on Cloudflare Workers without authentication. Supports custom tools and connections to Cloudflare AI Playground and Claude Desktop.

Records and scores prospective equity earnings predictions made by AI agents, allowing comparison of different agent configurations.

Enables AI agents to monitor website performance by scanning sites, retrieving Core Web Vitals, detecting regressions, and receiving AI-powered optimization recommendations.

Manage posts, channels, organizations, and ideas through any MCP-compatible LLM client.

A local MCP server for cross-repository semantic code intelligence in TypeScript and Go, backed by a persistent LadybugDB graph.

MCP server that extracts YouTube video transcripts (including metadata) as Markdown, enabling AI to summarize and discuss video content without watching it.

Convert URL to PDF suitable for mobile reading.

Enables AI assistants to manage VergeCMS blogs through natural language, providing complete CRUD operations for blogs and articles with secure browser-based authentication and automatic token persistence.

Enables AI assistants to perform real network diagnostics on the local machine, including ping, traceroute, DNS lookups, TLS checks, and more.

A fullstack MCP server-client pipeline