Codex Delegate MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| delegateA | Delegate a coding task to OpenAI Codex. Never run codex from the shell — use this tool. Check status before trusting result — a run that spawns then fails returns normally. Keep model, reasoningEffort and fast at their defaults unless the user asks. See the delegate skill. |
| cancelA | Cancel active runs. delegationId selects one (announced in progress before spawn — the only handle if a run wedges at startup), threadId all on its thread, neither all. Waits for settlement; if a process tree survives the kill deadline, it still returns and the delegate result warns. Status: cancelled, nothing-active, or not-found (no active run with this ID). |
| doctorA | Diagnose plugin/CLI/login, recursion, and workspace (default: server cwd). deep adds no-quota help and model-catalog checks. |
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 3 tools
The three tools map to clearly distinct purposes: delegate starts a Codex run, cancel terminates active runs, and doctor diagnoses environment/plugin health. There is no realistic chance of selecting the wrong one for a given intent.
All three names are single lowercase imperative verbs (delegate, cancel, doctor), which is a consistent, predictable style. There's no verb_noun structure, but the convention is uniform enough to be readable.
Three tools fit a deliberately narrow delegation-focused server, with each tool earning its place (start, stop, diagnose). It is slightly thin and leaves no room for status/inspection, but is reasonable for the stated scope.
The surface covers starting, cancelling, and diagnosing runs, but there is no explicit status or list-runs tool even though delegate's description tells agents to 'check status before trusting result'. This leaves a notable gap for inspecting or enumerating runs.