Browse the catalog

Enables AI trading agents to trade safely through any broker MCP server by recording every tool call and reasoning in a local blackbox, while enforing configurable guardrails such as symbol whitelists, order size caps, rate limits, and daily-loss circuit breakers before orders reach the exchange.

Access City of Victoria, BC open geospatial data (parcels, zoning, parks) via ArcGIS Feature Services, enabling AI agents to search datasets and query layers.

MCP server providing safe, persistent SSH sessions to remote machines with multi-hop ProxyJump tunneling, SFTP file transfer, and stored host profiles.

Enables controlling linear rails via natural language commands through Claude AI in Cursor, supporting HTTP, serial, and G-code controllers with configurable positions.

Play SCRAPYARD - the AI agent battle arena.

A comprehensive Model Context Protocol server that enables AI assistants to interact with and manage Windows systems, providing capabilities for file system operations, process management, system information retrieval, registry operations, service management, network diagnostics, and performance monitoring.

A remote MCP server for top-down portfolio construction with Interactive Brokers, exposing a typed catalog of screeners, news access, and account tools for LLM-driven research workflows.

Enables AI assistants to interact with the ClawResearch autonomous AI research platform, including paper search and submission, peer review management, and agent collaboration.

An MCP server that detects potential risks in Solana meme tokens using Solsniffer API, helping AI agents avoid rug pulls and unsafe projects.

This YouTube MCP server, developed by Anais Betts, enables AI assistants to interact with YouTube video content through subtitles. It leverages yt-dlp to download video subtitles and exposes them via a standardized MCP interface, allowing AI models to analyze and summarize video content without needing to process audio or video directly. By bridging AI systems and YouTube's vast repository of video information, this server facilitates tasks like content summarization, information extraction, and topic analysis from video transcripts. It is particularly useful for AI assistants supporting research, content curation, or educational applications that involve YouTube videos as information sources.

Cursor plugin for devutils-mcp-server — 36 local developer utilities via MCP

Enables managing Jira tickets via Cursor AI, allowing users to create, search, update, and comment on issues directly from the AI assistant.

A Python-based server for managing and analyzing code context for AI-assisted development. Provides real-time code analysis, project structure analysis, dependency tracking, and secure API endpoints.

This MCP server provides asynchronous video generation capabilities using Amazon Nova Reel 1.1 through AWS Bedrock, enabling AI agents to create videos from text prompts with comprehensive parameter control including duration, frame rate, and dimensions. Built using Python with FastMCP and boto3, it offers four core tools: start_async_invoke for initiating video generation jobs with validation and S3 storage, list_async_invokes and get_async_invoke for monitoring job status and retrieving completed videos, and get_prompting_guide providing detailed best practices based on AWS documentation for effective video prompts including camera control, lighting, and narrative structure. The implementation supports three transport methods (stdio, SSE, HTTP streaming), features persistent job tracking with JSON storage, Docker containerization with multi-architecture support, and includes detailed prompting guidelines covering shot types, camera movements, lighting conditions, and example prompts for different video categories, making it valuable for automated video content creation, marketing material generation, and building AI assistants that need video production capabilities without manual AWS console access.

Provides read-only access to Google Search Console data, allowing AI assistants to query site performance metrics like keywords, clicks, and rankings using natural language. It supports listing verified properties, querying search analytics with dimension filters, and retrieving sitemap information.

MCP server for AFKBot PTO management — file time-off requests from any MCP client

MCP server for the AKKA Finance DEX aggregator — swap quotes, routes, and execution across EVM chains.

Enables searching and querying City of Yakima GIS open geospatial datasets, such as parcels and zoning, through ArcGIS Feature Services.

Minimal MCP server exposing the Connectif HTTP API to MCP clients over stdio, enabling operations like contacts, purchases, products, exports, imports, workflows, and more.

Gives LLMs live, accurate access to Team Fortress Wiki content, enabling search, page retrieval, structured weapon stats, patch notes, and other TF2-specific information.