MCP Servers

MCP server for code-mode — execute TypeScript code chains with pre-configured tools in an isolated sandbox

MCP server that gives AI assistants (Gemini, Claude, Cursor, Windsurf, Copilot) deep understanding of your codebase — 10 tools + persistent

MCP server that analyzes codebases and extracts symbols for LLM consumption

Visual code workflow explorer for coding agents. Builds deterministic, source-grounded Mermaid flowcharts via MCP, local-first, with no API

MCP server for comprehensive GitHub repository analysis using Gemini AI

MCP server that gives AI assistants persistent understanding of your codebase

Codemend MCP server — connect Claude Code and AI tools to your production error monitoring

MCP (Model Context Protocol) server providing AI coding agents with universal, language-agnostic development rules. Includes coding

Project-aware MCP server that brings Google CodeWiki documentation into coding agents (Claude Code, Cursor, VS Code, Codex CLI, Gemini CLI

Minimal TypeScript MCP server that proxies prompts to Codex and Gemini CLI

MCP server for orchestrating parallel OpenAI Codex CLI tasks with git worktree isolation

Symbol-aware memory server for Codex and other coding agents.

MCP server for vision analysis through ChatGPT/Codex OAuth credentials

Codex plugin exposing xAI/Grok OAuth and API-key tools through a local MCP server.

Standalone MCP server + client for generating Anima-style images via a remote/local ComfyUI Server API.

Command Cloud MCP Server — read-only access to Setup, Dispatch, Billing, Supply, and Telematics APIs

MCP server for Compass DaaS - explainable dietary intelligence for AI agents

AI Compliance Calendar MCP server — track AI regulations, deadlines, risk assessments, and policy updates across jurisdictions (EU, US, UK

Model Context Protocol server for complyeah — trigger external penetration tests and read scans, findings, and domains from any

Screenshot → reusable Tailwind components. MCP Server for AI-powered UI component extraction. Works with Claude, Cursor, Windsurf, Copilot.

A drop-in confidence gate for LLM agents: turn token logprobs into an accept / verify / ask-a-human routing decision, with honest per-model