Browse the catalog

mcp\_3d\_relief

Freshdesk MCP Pack — helpdesk ticket and contact management via Freshdesk API v2.

VS Code Copilot database MCP — add a free cloud database to GitHub Copilot agent mode via mcp.json

MCP server for rendering 35+ diagram types — sequence, flowchart, ER, C4, gantt, mindmap, infra, and more — to SVG/PNG with browser preview. Local rendering with palette/theme support and shareable diagrammo.app URLs.

This MCP server provides AI assistants with read-only access to Kubernetes clusters through a comprehensive set of tools for resource inspection, log retrieval, and metrics monitoring, built using Go with the Kubernetes client-go library and supporting both stdio and SSE transport modes. The implementation offers 10 tools including resource listing with filtering, detailed resource inspection, advanced pod log retrieval with grep patterns and time filtering, API resource discovery, context management, node and pod metrics collection, and base64 encoding utilities, all while maintaining strict read-only security to prevent destructive operations. Built with automatic connectivity validation, per-command context switching, and client-side pagination for metrics, it serves DevOps teams needing AI-assisted cluster troubleshooting, developers requiring safe cluster inspection capabilities, and organizations wanting to enable AI assistants to help diagnose Kubernetes issues without modification risks.

Enables resolving genetic variant identifiers (HGVS, dbSNP, ClinVar, gnomAD) to stable ClinGen Allele Registry IDs (CA#) and cross-references, providing a canonical allele identity across genome builds.

A Model Context Protocol server that combines DeepSeek R1's reasoning capabilities with Claude 3.5 Sonnet's response generation, enabling two-stage AI processing where DeepSeek's structured reasoning enhances Claude's final outputs.

Enables grounding AI responses in a local document corpus by exposing MCP tools to list, search, and summarize documents, and generating answers using OpenAI.

MCP server for the Elsevier Developer APIs. Gives Claude Code access to Scopus, ScienceDirect, and other Elsevier academic databases.

MCP server that provides a live, terminal-native layered dependency map for AI coding assistants, with tools to track and visualize development progress in real time.

A stock research MCP server that enables natural-language queries for market data, watchlist management, company analysis, and research note tracking, using FastMCP and Databricks Lakebase Postgres.

Enables interaction with the PayHere payment gateway via MCP, allowing payment retrieval, refund issuance, checkout payload generation, and signature computation/verification.

Connects Claude Desktop to Google Drive, allowing Claude to access and interact with your Drive files and folders securely through OAuth authentication.

A structured memory management server that maintains living documents as markdown files for focused, domain-specific projects like travel planning, research, or real estate search. Unlike traditional semantic search approaches that scatter information across conversation snippets, this implementation organizes information into structured sections that can be systematically updated, searched, and tracked over time. The server automatically creates backups, supports flexible markdown formatting, and provides tools for adding items to lists, moving content between sections, and searching within documents, making it particularly valuable for accumulating and organizing context around specific areas of focus that evolve through multiple conversations.

This MCP server by maxbogo addresses the fundamental problem that LLMs struggle with generating truly random numbers due to their deterministic nature and training biases, as demonstrated by distribution analysis showing clear patterns in random number generation from popular LLMs like Claude, Gemini, and OpenAI. The implementation provides a single tool that fetches genuinely random numbers from Random.org's atmospheric noise-based API, supporting customizable ranges with proper validation and error handling. It's particularly valuable for applications requiring true randomness such as statistical sampling, gaming, cryptographic operations, or any scenario where LLM-generated pseudo-randomness would introduce unwanted bias or predictability.

PBS MCP Server provides access to the Australian Pharmaceutical Benefits Scheme (PBS) API through a standalone server that enables AI models to query pharmaceutical data including medicine listings, pricing, and availability. Developed by Matthew Cage, founder of AI-Advantage.au, this TypeScript implementation offers multiple interfaces including stdio, HTTP/SSE, and a command-line tool with comprehensive error handling for API rate limits. The server supports various PBS endpoints such as prescribers, item-overview, and schedules, making it particularly valuable for healthcare applications, medication research, and integrating up-to-date pharmaceutical information directly into AI workflows without requiring the data in the model's training.

MCP server that exposes an analyze_image tool using Gemini vision models to describe or analyze images from local paths, URLs, or base64 data URIs.

Provides live cryptocurrency market data from over 100 exchanges, enabling AI agents to fetch prices, order books, funding rates, and more for trading analysis and arbitrage opportunities.

Detects Chinese mobile phone number carriers (China Mobile, China Unicom, China Telecom, etc.) and their geographical location (province and city) using a database of 492,088 records. Supports both single and batch number detection (up to 100 numbers).