# codex-subagent-mcp

Local MCP server that delegates coding tasks to the OpenAI Codex CLI, with explicit model and reasoning-effort selection.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.5.0
- **Author:** Paris Niarfe Baltazar Salguero
- **License:** MIT
- **npm:** codex-subagent-mcp
- **Source:** https://github.com/parisbs/codex-subagent-mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 2 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-03T19:50:48.953Z
- **Version scanned:** 0.5.0
- **CVEs:** none found by OSV at scan time

## Tools

8 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `codex_doctor` — Check whether the local Codex CLI is installed, recent enough, signed in and able to load its configuration, and report the exact
- `list_codex_models` — List the Codex models available on this machine, with the reasoning-effort levels each one supports.
- `codex_recommend` — Given a task description, recommend which Codex model and reasoning effort to delegate it with.
- `codex_delegate` — Delegate a task to the local Codex CLI (OpenAI's coding agent), choosing model and reasoning effort.
- `codex_follow_up` — Send a follow-up message to a previous delegation using its thread_id. Codex retains the earlier context,
- `codex_job_status` — Report the state and recent activity of a background delegation started with mode=background.
- `codex_job_result` — Return the full output of a finished background delegation. Errors if the job is still running.
- `codex_job_cancel` — Terminate a running background delegation.

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"codex-subagent\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"codex-subagent-mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 13, ceiling 31 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/codex-subagent-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/codex-subagent-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/codex-subagent-mcp
- HTML page: https://forgeregistry.com/registry/codex-subagent-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.