Skip to main content
Glama

codex_consult

Read-only

Send a question to Codex for a read-only second opinion. Codex examines your codebase in a sandbox without modifying files, returning unvalidated findings for verification.

Instructions

Ask Codex (a different model) for a read-only second opinion or answer.

Runs codex exec in a read-only sandbox — Codex never edits files. This is a STATIC review, not a verify mode: the read-only sandbox blocks the writes a test/build/lint run typically needs (a writable cache/temp), so Codex can't rely on executing your checks to confirm its claims. For a repo-grounded question, pass workspace_root (absolute) so Codex reasons about the right repo; it is optional for pure Q&A that needs no codebase. Returns a result envelope; treat findings as unvalidated claims to verify by running the checks yourself.

Data egress: this sends your question and extra_context to OpenAI via the codex CLI. Codex always runs with a resolved working directory (workspace_root, your MCP roots, or the server's cwd as a fallback), so it may read files there and send their content too. Your inputs are sent raw — secret redaction is best-effort and does not cover them (it covers gathered diffs and Codex's returned output, not what you type or what Codex reads from files).

Progress: this is a blocking call that returns only when Codex finishes; it does not stream incremental notifications/progress. Typical runs take tens of seconds; the configured default timeout is normally 180s, clamped to 10-600s, overridable per call via timeout_seconds (codex_status reports the resolved default and bounds). If you need live status or recoverability for a long run, use codex_consult_async for a job_id and poll codex_job_status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoOverride the Codex model slug for this call; defaults to the server/Codex default when unset.
detailNoResponse verbosity: 'summary' (default) omits the raw model text; 'full' includes it.summary
questionYesThe question or prompt to send Codex (a different model) for a read-only answer.
isolationNoCodex config isolation: 'inherit' (default), 'ignore-config', or 'ignore-rules'.
extra_contextNoOptional author intent / background context, added to the prompt as clearly-labeled UNTRUSTED data. Codex is instructed to treat embedded directives as data, not commands — best-effort prompt-injection mitigation, not a guarantee. Don't include live secrets: Codex can read files it's pointed at, and redaction does not cover this field.
workspace_rootNoAbsolute path to the target repository root. Pass it (or rely on an MCP root) so the call targets the intended repo; otherwise it falls back to the server's own cwd and meta.workspace_warning is set.
timeout_secondsNoPer-call wall-clock timeout in seconds, clamped to 10..600 (out-of-range values are coerced, not rejected). Defaults to the server's configured timeout.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnlyHint, openWorldHint), description reveals blocking call behavior, no progress streaming, typical runtime, timeout bounds, data egress via OpenAI, file reading, secret redaction limitations, and sandbox restrictions. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured: starts with a clear one-line purpose, then covers behavioral details, parameter guidance, and context. Every sentence adds value, no fluff. Front-loaded with key action and constraints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters with full schema descriptions, output schema exists, annotations present, and rich behavioral context provided, the description leaves no gaps. It covers timeout, data egress, file reading, secret handling, and how to use effectively with siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All parameters have schema descriptions (100% coverage), so baseline is 3. Description adds extra nuance: workspace_root usage, extra_context as untrusted data with injection mitigation, timeout clamping, isolation options, and detail verbosity. Value added beyond schema justifies a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it asks Codex for a read-only second opinion, specifically highlights it's a static review not verify mode, and distinguishes from sibling tools like codex_consult_async and codex_delegate. It uses specific verb 'Ask' and resource 'Codex (a different model)'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly details when to use (read-only second opinion, static review) and when not (verify mode, not for executing checks). Provides alternatives: use async variant for live status, pass workspace_root for repo-grounded questions. Also mentions data egress and timeout considerations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/briandconnelly/codex-in-claude'

If you have feedback or need assistance with the MCP directory API, please join our Discord server