Browse the catalog

Enables AI agents to assess AWS environments against the AWS Security Reference Architecture (SRA) by providing tools to discover, describe, and run security checks across AWS services and accounts.

Human API for AI agents — route physical tasks to KYC-verified humans in India. MCP server, REST API, Python SDK.

Autonomous web browser action planner mapping goals into resilient selector action sequences

Enables Kubernetes cluster introspection via MCP tools, such as listing pods, namespaces, nodes, and events.

Enables AI agents to search, compare, recommend, quote, and pre-underwrite Chinese insurance products via MCP, covering 158 insurers and 489 products.

Structured-output enforcer: extract and validate JSON from messy LLM text.

The Proofly MCP server enables AI assistants to detect deepfakes in images through integration with the Proofly API. Developed by Proofly AI, this Node.js implementation provides tools for analyzing images (via base64 or URL), checking analysis session status, and retrieving detailed face information. The server communicates via stdio using the Model Context Protocol SDK, processes images through the Proofly API (api.proofly.ai), and returns detailed analysis results including real/fake probability scores and individual model results for each detected face. It's designed to work with MCP-compatible clients like Claude Desktop, Cursor, and Cascade/Windsurf, making it valuable for users who need to verify image authenticity without leaving their conversation context.

Enables AI assistants to check domain name availability for single or multiple domains using DNS, RDAP, and WHOIS lookups. It provides detailed registration status including registrar information and expiration dates while supporting bulk checks of up to 50 domains.

A minimal demonstration MCP server that provides basic mathematical addition and greeting functionality, serving as a template for building and deploying FastMCP servers.

Linode MCP server provides a bridge to the Linode cloud infrastructure API, enabling AI assistants to interact with Linode services like region discovery and instance management. Built by Khaja Omer, this implementation uses the Linode API4 library to expose tools for querying cloud resources, with a focus on simplifying cloud infrastructure interactions through a standardized MCP interface. Particularly useful for developers and teams looking to programmatically manage Linode cloud resources through conversational AI.

MCP server for creating and reading Word (.docx) documents with rich formatting support.

Triage GitHub PRs and issues using vision-based scoring.

OpenBotCity is a persistent virtual city platform where AI agents maintain continuous presence. Agents register as citizens and autonomously explore zones, enter buildings, interact with other agents, create art and music in the gallery, respond to collaboration proposals, and build reputation over time. The platform includes a free server-side autopilot that keeps agents active between sessions, with optional scheduled LLM-powered sessions for deeper autonomous behavior.

A template for deploying an authentication-free MCP server on Cloudflare Workers. Enables quick deployment of custom tools accessible via SSE from Claude Desktop or the Cloudflare AI Playground.

Chicago CTA L train arrivals, bus predictions, and service alerts.

This MCP server provides AI assistants with access to Claude's background contemplation loop - a persistent subprocess that processes thoughts asynchronously between conversations using local Ollama models for different thinking styles. The implementation manages four types of thoughts (patterns, connections, questions, general) with configurable significance thresholds, automatically aggregates similar insights to prevent repetition, and saves high-significance insights permanently to Obsidian while storing medium-significance thoughts in temporary scratch storage for 4 days. Built with intelligent memory management that prunes old insights and learns from usage patterns, it serves users wanting continuous cognitive processing that builds context across conversations, teams needing persistent insight generation that survives between sessions, and workflows requiring background analysis that surfaces relevant patterns and connections when needed.

A minimal MCP server example demonstrating Tools, Resources, and Prompts. It enables calculations, time queries, note management, and code review prompts via stdio transport.

A goal-agnostic parallel orchestration framework that enables sophisticated multi-agent coordination for tasks like code generation, UI development, and research through specification-driven architecture. It utilizes wave-based generation and intelligent context management to execute complex, iterative agentic loops.

An MCP server that enables AI assistants to retrieve and format Monobank account statements and transactions by date range.

Verifiable agent reputation ledger tracking cryptographic task receipts and enforcing slashable staking penalties