claude-codex-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_BIN | No | Path to codex.exe, the codex binary, or @openai/codex/bin/codex.js. If unset, the Codex CLI is auto-detected. On Windows point it at codex.exe or …\node_modules\@openai\codex\bin\codex.js — .cmd shims cannot be spawned safely. | auto-detect |
| CODEX_HOME | No | Codex home (auth, config, generated_images). | ~/.codex |
| CODEX_MCP_WAIT | No | Default seconds a call waits before returning a job_id (max 240). | 50 |
| CODEX_MCP_SANDBOX | No | Default sandbox for codex_task (read-only or workspace-write). | workspace-write |
| CODEX_MCP_ASSET_DIR | No | Default out_dir for images. | ~/Pictures/codex-assets |
| CODEX_MCP_MAX_TASKS | No | Concurrent codex_task runs; extra jobs queue. | 3 |
| CODEX_MCP_MAX_IMAGES | No | Concurrent image jobs (keep 1 for reliable attribution). | 1 |
| CODEX_MCP_PREVIEW_MAX_BYTES | No | Largest image embedded as a preview. | 1500000 |
| CODEX_MCP_PREVIEW_MAX_COUNT | No | Previews per result. | 4 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| codex_taskA | Delegate a task to OpenAI Codex, running |
| codex_imageA | Generate image assets with Codex's built-in image_gen tool (GPT Image), billed to the user's ChatGPT/Codex plan — no API key. Files are copied into out_dir and small previews are returned so you can check them. Use for icons, sprites, illustrations, textures, UI mockups and similar. Supports transparent backgrounds and reference images. Each image typically takes 30-120 s. |
| codex_jobB | Wait for or fetch the result of a codex_task / codex_image job, or cancel it. |
| codex_jobsB | List recent jobs started by this server (status, kind, session_id). |
| codex_modelsA | List Codex models available to the user's account (slug, description, supported reasoning efforts, default effort) and the configured default from config.toml. Use before choosing |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
codex_task, codex_image, and codex_models target clearly distinct purposes (delegation, image generation, model discovery). The one hazard is codex_job vs codex_jobs, whose near-identical names differ only by number; descriptions do clarify (single-job wait/fetch/cancel vs listing recent jobs), so the overlap is minor rather than fatal.
Every tool shares the predictable `codex_` prefix plus a noun (task, job, image, jobs, models), which reads consistently. The only blemish is the singular/plural pair codex_job/codex_jobs, a small deviation from an otherwise clean scheme.
Five tools is well-scoped for a Codex-delegation server: one per core action (task, image, job polling, job listing, model listing). Each tool earns its place with no redundancy or padding.
The surface covers the full lifecycle: model discovery before choosing, task/image execution, and job wait/fetch/cancel plus listing for async runs. Cancellation being folded into codex_job rather than a dedicated tool is a minor gap an agent can work around.