MCP servers for Codex CLI

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

Build MCP servers from natural language prompts — local-first, privacy-focused

AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)

Governed MCP gateway: approved tools only, each call policy-checked and recorded per agent

Self-healing API proxy MCP — your API calls, but they never actually break.

przm Voice — adaptive personality MCP server for AI agents. Part of the przm AI reliability suite. Evolving personality from behavioral

Award-level creative frontend AI brain — GSAP, Three.js, Lenis, Barba, Design Intelligence

An MCP-compatible server for querying public transport data in Europe (UK, CH, BE, NO).

Publish structured, AI-readable business identity data as an MCP server in minutes.

Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.

TTS MCP server and CLI for language learning (ElevenLabs, AWS Polly, OpenAI)

OmniFocus MCP server and CLI tool for macOS task management with AI assistants

Universal Python code execution MCP server - one tool to rule them all

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.

Local QA agent — maps frontend routes to backend API calls, probes every endpoint live, scores pages 0–100, explains why data is missing

Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.

Autonomous QA agent - runs browser-based tests via MCP

Qantara (arched bridge): an MCP bridge that lets coding agents (Claude Code, Codex, Gemini) delegate tasks to each other.

QoutaMCP - MCP server for inspecting and analyzing project structures - detects languages, frameworks, entry points, and dependencies

Local code intelligence foundation: structural code graph, LanceDB semantic layer, retrieval, context packing, and MCP tools.

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.