Browse the catalog

Starknet MCP server.

Provides a shared operational layer for managing tasks and project context across Claude Desktop surfaces. Tasks and contexts are stored as plain markdown files, enabling task creation, completion tracking, filtering by status and tags, and project context persistence without a database.

Enables searching and analyzing CVEs and vulnerabilities from multiple sources, optimized for PR review scenarios to help developers identify the latest security issues.

MCP server for the Lattice container orchestration platform, enabling Claude Code to manage workers, stacks, containers, and deployments through natural language.

Provides structured access to Solana Anchor error data, enabling AI coding agents to parse logs, debug transactions, and look up error codes.

Provides image understanding capabilities by analyzing single or multiple images (local files, URLs, or base64) via MiniMax VL API, complementing text-only models.

This MCP server implementation provides a bridge to MySQL databases, enabling AI assistants to execute SQL queries, analyze database schemas, and generate business insights. Developed by zajTools, it offers tools for reading and writing data, managing tables, and appending discovered insights to a continuously updated memo. The server is designed for use cases requiring AI-driven database interaction and business intelligence, such as data analysis, report generation, and automated insight discovery.

An MCP server that exposes five tools for generating verified electronic circuit documentation, including netlist verification, component lookup, and generation of schematics, boards, and renders.

This Salesforce MCP server by Cristiano Steffens provides AI agents with comprehensive Salesforce integration through TypeScript, offering 11 core tools for SOQL queries, SOSL searches, record CRUD operations, object metadata retrieval, and REST API access. Built with robust authentication supporting both username/password OAuth flows and direct access token methods, it includes automatic token refresh, comprehensive error handling, and Docker deployment with multi-architecture support for both sandbox and production environments. The implementation features extensive test coverage with Vitest, TypeScript strict mode for type safety, and flexible configuration through environment variables, making it valuable for AI-powered CRM automation, data analysis workflows, and applications requiring programmatic Salesforce operations with enterprise-grade reliability.

Bridges AI agents with the Codex CLI while preserving session continuity. Creates real, resumable Codex CLI sessions via MCP calls that survive server restarts. Provides three primary tools: general conversation (codex_chat), structured planning with critique (codex_plan), and code review (codex_review). Features automatic attribution distinguishing agent requests from human commands, per-request model and reasoning effort overrides, and session storage in Codex's native format for manual resumption with `codex resume`.

Enables AI assistants to interact with Ed Discussions (EdStem) course discussions, manage threads, comments, and facilitate Q&A, with tools for analytics and read status control.

Geopolitical conflict risk, political events, and maritime traffic data for AI agents

Search 100K+ EDC products. Track drops, compare prices, and analyze market trends.

Delivers desktop notifications triggered by AI agents over stdio transport. Provides a simple interface for sending system-level notifications to keep users informed of agent activity and task completion without polling.

MCP server for finding nearby public toilets in Seoul, with real-time open status and accessibility filters.

Access OpenRouter models through MCP

This read-only MCP Server allows you to connect to Google AdWords data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

A sample implementation of Model Context Protocol server demonstrating core functionality with simple arithmetic tools and greeting resources.

MCP server that compresses markdown files into caveman-style prose, cutting token usage by 65% while preserving code and structure.