valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add more detailed documentation on MCP server usage (#3345)

Browse Source 
Adds further information on how to get started with `codex mcp`:
- Tool details and parameter references
- Quickstart with example using MCP inspector.
This commit is contained in:
Charlie Weems
2025-09-11 14:38:24 -07:00
committed by GitHub
parent 027944c64e
commit 8f7b22b652
1 changed files with 45 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
docs/advanced.md
View File

@@ -38,5 +38,49 @@ args = ["-y", "mcp-server"]
env = { "API_KEY" = "value" }
```
## Using Codex as an MCP Server
The Codex CLI can also be run as an MCP _server_ via `codex mcp`. For example, you can use `codex mcp` to make Codex available as a tool inside of a multi-agent framework like the OpenAI [Agents SDK](https://platform.openai.com/docs/guides/agents).
### Codex MCP Server Quickstart
You can launch a Codex MCP server with the [Model Context Protocol Inspector](https://modelcontextprotocol.io/legacy/tools/inspector):
``` bash
npx @modelcontextprotocol/inspector codex mcp
```
Send a `tools/list` request and you will see that there are two tools available:
**`codex`** - Run a Codex session. Accepts configuration parameters matching the Codex Config struct. The `codex` tool takes the following properties:
Property | Type | Description
-------------------|----------|----------------------------------------------------------------------------------------------------------
approval-policy | string | Approval policy for shell commands generated by the model: `untrusted`, `on-failure`, `never`.
base-instructions | string | The set of instructions to use instead of the default ones.
config | object | Individual [config settings](https://github.com/openai/codex/blob/main/docs/config.md#config) that will override what is in CODEX_HOME/config.toml.
cwd | string | Working directory for the session. If relative, resolved against the server process's current directory.
include-plan-tool | boolean | Whether to include the plan tool in the conversation.
model | string | Optional override for the model name (e.g. "o3", "o4-mini").
profile | string | Configuration profile from config.toml to specify default options.
**prompt** (required) | string | The initial user prompt to start the Codex conversation.
sandbox | string | Sandbox mode: `read-only`, `workspace-write`, or `danger-full-access`.
**`codex-reply`** - Continue a Codex session by providing the session id and prompt. The `codex-reply` tool takes the following properties:
Property | Type | Description
-----------|--------|---------------------------------------------------------------
**prompt** (required) | string | The next user prompt to continue the Codex conversation.
**conversationId** (required) | string | The id of the conversation to continue.
### Trying it Out
> [!TIP]
> It is somewhat experimental, but the Codex CLI can also be run as an MCP _server_ via `codex mcp`. If you launch it with an MCP client such as `npx @modelcontextprotocol/inspector codex mcp` and send it a `tools/list` request, you will see that there is only one tool, `codex`, that accepts a grab-bag of inputs, including a catch-all `config` map for anything you might want to override. Feel free to play around with it and provide feedback via GitHub issues.
> Codex often takes a few minutes to run. To accommodate this, adjust the MCP inspector's Request and Total timeouts to 600000ms (10 minutes) under ⛭ Configuration.
Use the MCP inspector and `codex mcp` to build a simple tic-tac-toe game with the following settings:
**approval-policy:** never
**prompt:** Implement a simple tic-tac-toe game with HTML, Javascript, and CSS. Write the game in a single file called index.html.
**sandbox:** workspace-write
Click "Run Tool" and you should see a list of events emitted from the Codex MCP server as it builds the game.