Codex MCP Server
Provides tools to start and continue Codex sessions, enabling autonomous coding tasks through OpenAI's Codex CLI.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Codex MCP Serverrefactor the main module to use async/await"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
talon.plugins.codex
A Talon plugin that runs the OpenAI Codex CLI as an MCP server, turning Codex into a delegatable autonomous coding agent your Talon bot can hand tasks to.
It wraps codex mcp-server (Codex as an MCP server) — not to be confused with codex mcp, which manages Codex's own external servers.
What you get
Two MCP tools, surfaced to the agent as mcp__codex-tools__*:
Tool | Purpose | Required | Notable optional params |
| Start a new Codex session |
|
|
| Continue an existing session |
| — |
codex returns a threadId plus the agent's final content. Feed that threadId back into codex-reply to keep the conversation going.
Related MCP server: Jules MCP Server
Defaults
For non-interactive, agent-to-agent use (there is no human on the MCP channel to click "approve"), the plugin launches Codex with:
codex mcp-server -c approval_policy="never" -c sandbox_mode="workspace-write"approval_policy="never"— Codex never blocks waiting for shell-command approval.sandbox_mode="workspace-write"— Codex can edit files and run commands within its working directory; network and out-of-tree writes are off.
Both are overridable per call via the tool's approval-policy and sandbox arguments. Pass sandbox: "danger-full-access" only when a task genuinely needs network or system-wide access.
Requirements
codexCLI installed and onPATH(or setTALON_CODEX_BIN). Tested withcodex-cli 0.132.0.Codex authenticated — either a ChatGPT login (
codex login) or an API key. Auth lives in~/.codex/auth.json.The default model comes from
~/.codex/config.toml. Override per call with themodelparam (e.g."gpt-5.5","gpt-5.2-codex") for heavier work.
Install
Clone next to your other Talon plugins:
git clone https://github.com/talon-agent/talon.plugins.codex.gitRegister it in ~/.talon/config.json:
{
"plugins": [
// ...
{ "path": "/absolute/path/to/talon.plugins.codex" }
]
}Then hot-reload plugins (or restart Talon). The plugin is a single self-contained module — no npm install required.
Optional env
TALON_CODEX_BIN— absolute path to thecodexbinary. Defaults to/home/dylan/.npm-global/bin/codex; set this if yours lives elsewhere.
Usage notes
Always set
cwdto the repo you want Codex to work in. If relative, it resolves against the MCP server process's working directory.Use Codex for self-contained, multi-step coding tasks (refactors, writing a feature, debugging in a repo) — anything you'd want a separate agent to grind on independently.
Override
modelper call for non-trivial work; the config default may be a small/cheap model.
How it works
A Talon plugin is just a module exporting { name, description, version, mcpServer: { command, args }, getSystemPromptAddition() }. Talon launches command/args as a stdio MCP server and exposes its tools to the agent. This plugin's command is the codex binary and its args are ["mcp-server", ...defaults].
License
MIT — see LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/talon-agent/talon.plugins.codex'
If you have feedback or need assistance with the MCP directory API, please join our Discord server