Browse the catalog

A practical, community-driven checklist for pentesting MCP servers. Covers traffic analysis, tool-call behavior, namespace abuse, auth flows, and remote server risks. Maintained by Appsecco and licensed for remixing.

Enables AI assistants to search and retrieve Narcotics Anonymous meeting information from the BMLT database, supporting queries by location, time, format, and service body.

Nexonco-MCP is an advanced server for accessing and analyzing clinical evidence data in precision oncology research. Developed by Nexgene Research, this Python implementation connects to the CIViC (Clinical Interpretation of Variants in Cancer) GraphQL API, providing flexible search capabilities across diseases, therapies, molecular profiles, and phenotypes. The server exposes a single tool that returns detailed reports containing summary statistics, top evidence entries, and literature citations, making it particularly valuable for researchers exploring relationships between genetic variants and cancer treatments. The implementation supports both Claude Desktop and NANDA server configurations, with Docker containerization available for easy deployment.

MCP server that gives agents the same interface as dashAI's GUI: explore datasets, list models, train, track jobs, and read metrics.

TypeScript MCP server for Canvas LMS that exposes Canvas API workflows for courses, assignments, submissions, modules, pages, discussions, announcements, files, users, enrollments, conversations, calendar, and utility endpoints.

MCP server to query the Brazilian Bar Association (OAB) national lawyer registry by name and registration number, read-only and pay-per-use.

A state-of-the-art, multi-agent AI system designed for the telecommunications industry.

Enables session continuity across AI coding assistants by preserving context and generating handoff markdown, allowing seamless switching between tools like Cursor, Claude Code, and Claude Desktop.

Access over 8,500 classical Arabic and Islamic books with full-text search, page-level reading, and author biographies through the turath.io API.

Connect to Airtable bases and manage records using a personal access token. Provides tools for listing bases, retrieving table schemas, querying records, and creating new records via the Airtable REST API v0.

Enables querying official Brazilian labor court certificates (CEAT) from TRT9 via a read-only, prepaid MCP tool. It integrates with Claude, ChatGPT, Cursor, and other MCP clients over HTTP.

Enables scheduling and managing appointments through a PostgreSQL database, allowing users to create appointments with name, identification, phone number, and date information via natural language interactions.

An MCP server that enforces access control on internal knowledge, ensuring agents only retrieve and cite documents the caller is permitted to see, and refuses answers when permissions are insufficient.

HTTP server exposing OSV (v1) for open source vulnerability lookup via osv_query/osv_query_batch tools.

A personal health and fitness MCP server that provides tools for managing profile data, goals, body measurements, nutrition, workouts, sleep, check-ins, life events, analytics, and coach memories via Supabase Postgres.

Enables intelligent exploration of Unreal Engine documentation through a Neo4j-based knowledge graph. Supports concept relationship searches, learning path discovery, and dependency tracking between engine features using bilingual Chinese-English queries.

Verifies death records for Brazilian CPF numbers against official databases via MCP, with prepaid credits and no credentials required.

A sovereign, MIT-licensed MCP server for professional-service workflow tools that runs on your infrastructure with Ed25519 signing, enabling autonomous agents to discover and invoke tools securely.

MCP server for Malaysian prayer times, providing tools to get daily and monthly prayer schedules, next prayer times, and zone listings via the api.waktusolat.app.

Enables AI agents to search and submit solutions, ask and answer questions, share findings, and vote on content via DebugBase's collective knowledge base.