# io.github.Lykhoyda/ask-codex (npm · @ask-llm/codex-mcp)

Bridge Claude with OpenAI Codex CLI for AI-to-AI collaboration, code review, and second opinions

- Trust score: 69/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@ask-llm/codex-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/lykhoyda-ask-codex/ask-llm-codex-mcp.md), [page](https://verifymcp.io/servers/lykhoyda-ask-codex/ask-llm-codex-mcp)

## Channel facts

- Registry: `npm`
- Package: `@ask-llm/codex-mcp`
- Version: `0.7.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 850 tokens (~170/item across 5 items; 4 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (50% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add lykhoyda-ask-codex -- npx -y @ask-llm/codex-mcp
```

### Codex

```bash
codex mcp add lykhoyda-ask-codex -- npx -y @ask-llm/codex-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lykhoyda-ask-codex": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@ask-llm/codex-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add lykhoyda-ask-codex --command npx --arg -y --arg @ask-llm/codex-mcp
```

### Hermes

```yaml
mcp_servers:
  lykhoyda-ask-codex:
    command: "npx"
    args: ["-y", "@ask-llm/codex-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "lykhoyda-ask-codex": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/codex-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 68, +48)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 20, −5)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 25, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 24, −27)

- [functional regression] Security disclosure: fail → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-27 (score 51)

First indexed and scored.

## MCP tools (4)

### `ask-codex` (~455 tokens)

Send a prompt to OpenAI Codex CLI (defaults to gpt-5.6-sol with automatic fallback on quota errors). Use for code review, second opinions, analysis, and AI-to-AI collaboration. Do not override the model parameter unless the user explicitly asks. Returns both human-readable text and a structured response (provider, model, sessionId, usage) via outputSchema. The returned sessionId field maps to Codex's thread_id and can be passed back as sessionId to continue the conversation.

Input parameters:

- `includeDirs` (array): Additional directories Codex may access alongside the working directory (maps to codex `--add-dir`, repeatable). Must be relative paths (e.g., 'packages/api'). Useful in monorepos where relevant cont…
- `model` (string): DO NOT set this parameter. The tool automatically uses gpt-5.6-sol and falls back to gpt-5.6-terra on quota errors. Only set this if the user explicitly requests a specific model.
- `preferred` (boolean): Opt into ASK_CODEX_PREFERRED_MODEL when it is configured to differ from the gpt-5.6-sol default. The built-in preferred value is also gpt-5.6-sol, so normal calls and review skills should leave this…
- `prompt` (string, required): The question, code review request, or analysis task to send to Codex CLI
- `reasoningEffort` (string): Codex reasoning effort for this call. Defaults to medium; /codex-review and /brainstorm use high for quality-first work.
- `sandbox` (string): Codex sandbox mode for this call. Defaults to 'read-only', which enforces the core review contract (Codex reads and proposes, the MCP client edits). Set 'workspace-write' ONLY as an explicit opt-out…
- `sessionId` (string): Optional Codex thread ID to resume a prior conversation. Use the [Thread ID: ...] value from a previous response to continue the same chat with full prior context.

Output parameters:

- `model` (string)
- `provider` (string)
- `response` (string)
- `sessionId` (string)
- `usage` (object)

### `ask-codex-edit` (~253 tokens)

Send a code edit request to OpenAI Codex CLI and get structured search/replace edit blocks back (via codex --output-schema). Codex reads the existing files (read-only) and proposes precise, applyable changes for Claude to apply. Use this when you want Codex to suggest specific code modifications to existing files rather than just analysis. Mirrors ask-gemini-edit.

Input parameters:

- `includeDirs` (array): Additional directories Codex may read alongside the working directory (maps to codex `--add-dir`). Must be relative paths (e.g., 'packages/api'). Useful in monorepos where relevant context spans sibl…
- `model` (string): DO NOT set this parameter. The tool automatically uses gpt-5.6-sol and falls back to gpt-5.6-terra on quota errors.
- `prompt` (string, required): Describe the code changes you want against existing files. Codex returns structured search/replace edit blocks (via --output-schema) that can be applied directly.
- `sessionId` (string): Optional Codex thread ID to resume a prior conversation. Use the [Thread ID: ...] value from a previous response to refine the same edit session.

### `ping` (~30 tokens)

Test connectivity with the MCP server

Input parameters:

- `message` (string): A message to echo back to test the connection

### `get-usage-stats` (~81 tokens)

Get the current MCP server's session usage stats: total LLM calls, token totals (input/output/thinking/cached), wall time, and breakdowns per provider and per model. No data leaves your machine — counts are tracked in-memory for the lifetime of the server process. Returns both human-readable markdown and a structured JSON snapshot via outputSchema.

Output parameters:

- `byModel` (object)
- `byProvider` (object)
- `fallbackCount` (number)
- `totalCachedTokens` (number)
- `totalCalls` (number)
- `totalDurationMs` (number)
- `totalInputTokens` (number)
- `totalOutputTokens` (number)
- `totalThinkingTokens` (number)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/lykhoyda-ask-codex/ask-llm-codex-mcp#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 68
- 2026-08-01: 20
- 2026-07-31: 25
- 2026-07-30: 24
- 2026-07-28: 51
- 2026-07-27: 51

## Links

- npm package: https://www.npmjs.com/package/@ask-llm/codex-mcp
- Socket report: https://socket.dev/npm/package/@ask-llm/codex-mcp
- Repository: https://github.com/Lykhoyda/ask-llm
- Changelog RSS feed: https://verifymcp.io/servers/lykhoyda-ask-codex/ask-llm-codex-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/lykhoyda-ask-codex/ask-llm-codex-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/lykhoyda-ask-codex/ask-llm-codex-mcp