Browse the catalog

Heroicons MCP Server exposes the popular Heroicons library as resources and tools for LLMs and agentic applications. Built with Bun and the MCP TypeScript SDK by SeeYangZhi, it provides tools for searching icons by name or category, listing all available icons, and generating usage examples for React applications. The server can run in both HTTP and stdio modes, making it compatible with Claude Desktop and other MCP clients. This implementation enables AI assistants to help developers find and implement the right icons for their web projects without needing to manually search through the Heroicons documentation.

Enables seamless integration with Trello boards, allowing users to manage cards, lists, and activities while automatically handling rate limiting and providing type safety.

MCP server for email deliverability — bounces, complaints and suppressions for SES, SendGrid, Mailgun, Postmark and more

Read-only MCP server for accessing Placera headlines, articles, company tags, and Telegram search data.

Reliable, scalable browser infrastructure for AI agents. Route, pool, and failover across any browser provider. 8 built-in browser tools using raw Chrome CDP - navigate, screenshot, snapshot, interact, evaluate. Zero-config with auto Chrome detection & concurrent sessions support

Enables automation of Affinity Photo, Designer, and Publisher from MCP clients, supporting document creation, layer editing, text replacement, export, and more via safe, validated tools.

MCP server implementation by Sam Wang that provides AI assistants with access to Perplexity.ai's search and reasoning capabilities through three specialized tools: perplexity_ask for conversational queries using the sonar-pro model, perplexity_research for comprehensive research with citations using sonar-deep-research, and perplexity_reason for complex reasoning tasks using sonar-reasoning-pro. Built with TypeScript and Express using streamable HTTP transport, the server includes session management for stateful connections, health monitoring endpoints, and Docker containerization for deployment. The implementation applies a system prompt that formats responses as either brief answers or structured suggestion lists, making it valuable for AI applications requiring real-time web search, academic research with proper citations, or complex analytical reasoning backed by current information from Perplexity's knowledge base.

Zoom MCP Server provides a bridge between AI assistants and the Zoom API, enabling management of virtual meetings through simple commands. Developed by Prathamesh Mane under the MIT license, this TypeScript implementation offers tools for creating, updating, deleting, and fetching Zoom meetings with proper authentication handling through OAuth. The server connects via stdio transport using the Model Context Protocol SDK, making it particularly valuable for scheduling and managing virtual meetings directly from AI assistants without requiring users to navigate the Zoom interface or understand the underlying API authentication flow.

Enables searching outdoor trails by name or place, retrieving route details, elevation profiles, and optional weather forecasts via Windy.

One API key, dozens of capabilities for your AI agent. Zero provider auth.

A thinking assistant MCP server that helps you reason through problems using structured frameworks like first principles and sequential thinking, starting wherever you are — clear, messy, or fragmentary.

Self-healing API proxy MCP that sends REST requests, diagnoses failures using Claude, patches requests, and retries. Successful fixes are remembered for instant reuse.

MCP server for compressing AI embeddings by 5-7x using TurboQuant (PolarQuant + QJL), with tools to compress, decompress, estimate savings, and embed+compress vectors.

Run AI market research: synthetic customer panels for concept testing, message testing, segments.

Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.

Provides tools for automated company research, competitor identification, and business model analysis to generate comprehensive business intelligence. It enables users to extract market keywords and synthesize competitive insights via AI-powered research capabilities.

A template project for building Model Context Protocol servers with FastMCP framework, Docker support, and example CRUD API implementation to help developers quickly bootstrap their own MCP servers.

Enables LLMs to query real-time Indian bank branch details, postal PIN codes, validate GSTIN/PAN structures, check e-commerce serviceability, and compute GST breakdowns using free public APIs and offline verification logic.

Moodle MCP Server provides an AI-powered interface for managing educational workflows within Moodle, enabling automated interactions with courses, students, assignments, and quizzes. Built with TypeScript and the Model Context Protocol SDK, it exposes tools for retrieving student information, managing assignments, and providing feedback, specifically designed to streamline administrative tasks for educators through natural language interactions.

An MCP server that gives an AI assistant a set of real mechanical-engineering tools. Provides deterministic tools like material properties, beam analysis, unit conversion, and curve fitting for engineering calculations.