MCP server that wraps OpenAI Codex CLI and exposes MCP API
Most developer tooling work still happens through a UI a human drives. Agentic Developer MCP MCP server moves it into the conversation instead. MCP server that wraps OpenAI Codex CLI and exposes MCP API.
This project wraps OpenAI's Codex CLI as an MCP (Model Context Protocol) server, making it accessible through the TeaBranch/open-responses-server middleware. This engine may be replaced with OpenCode or Amazon Strands
The server publishes 4 tools. What each one is for:
run_codex — Clones a repository, checks out a specific branch (optional), navigates to a specific folder (optional), and runs Codex with the given requestParameters — The Parameters tool exposed by this serverExample — The Example tool exposed by this serverclone_and_write_prompt — Clones a repository, reads the system prompt from .agent/system.md, parses modelId from .agent/agent.json, writes the request to a .prompt file, andInstallation goes through your MCP client rather than a global install: point it at @openai/codex on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
nvm install 22.15.1 | nvm use 22.15.1) required for CodexAmong the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agentic Developer MCP's toolset — run_codex, Parameters, Example and 1 more — is a fair guide to whether it matches your workflow. It is maintained by teabranch; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Agentic Developer MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| run_codex | Clones a repository, checks out a specific branch (optional), navigates to a specific folder (optional), and runs Codex with the given request. |
| Parameters | The Parameters tool exposed by this server. |
| Example | The Example tool exposed by this server. |
| clone_and_write_prompt | Clones a repository, reads the system prompt from .agent/system.md, parses modelId from .agent/agent.json, writes the request to a .prompt file, and invokes the Codex CLI with the extracted model. |
{
"mcpServers": {
"agentic-developer": {
"command": "npx",
"args": ["-y", "@openai/codex"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
nvm install 22.15.1 | nvm use 22.15.1) required for CodexBuild a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.