Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AUTH_MODENoAuthentication mode: 'chatgpt' or 'api'.chatgpt
LOG_LEVELNoLogging level (e.g., debug, info, warn, error).info
CODEX_MODELNoModel ID to use for reviews. Overrides review.model in the YAML config.
DB_MAX_ROWSNoFallback maximum rows for database connectors.
CODEX_BINARYNoPath or name of the Codex CLI executable.codex
JIRA_ENABLEDNoFallback enable/disable for a connector named 'jira'.
CODEX_SANDBOXNoSandbox mode for Codex execution.read-only
DB_TIMEOUT_MSNoFallback timeout in milliseconds for database connectors.
CODEX_EPHEMERALNoWhether to use an ephemeral Codex session.true
XDG_CONFIG_HOMENoBase directory where ~/.config/codex-mcp/ is looked for.~/.config
CODEX_MCP_CONFIGNoPath to the codex-mcp configuration file.~/.config/codex-mcp/codex-mcp.yaml
DATABASE_ENABLEDNoFallback enable/disable for a connector named 'database' or 'db'.
GIT_READ_ENABLEDNoWhether git read commands (diff, log, show, status, blame) are enabled.true
MAX_REVIEW_PASSESNoMaximum number of review passes.1
REVIEW_TIMEOUT_MSNoTimeout for a review in milliseconds.900000
MAX_ARTIFACT_BYTESNoMaximum size of artifacts in bytes.200000
CODEX_REQUIRE_MODELNoIf 'true', fail when the configured model is unavailable instead of falling back.false
CUSTOM_MCPS_ENABLEDNoFallback enable/disable for all connectors not named 'jira', 'database', or 'db'.
MAX_CANDIDATE_ITEMSNoMaximum number of candidate items per review.500
PROJECT_READ_ENABLEDNoWhether reading files from the project is enabled.true
CODEX_REASONING_EFFORTNoReasoning effort level for Codex reviews.high
MAX_CONCURRENT_REVIEWSNoMaximum number of concurrent reviews.2
PROJECT_MEMORY_ENABLEDNoWhether project memory is enabled.true

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

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
codex_qualifyA

Independently qualify candidate test cases and/or bug findings before you write your final artifact.

Send the candidate result you are holding in memory — do not write it to a file first, and do not call this after the report is published. codex-mcp runs Codex as a separate reviewer that inspects the repository itself, derives its own expected coverage or verdict, and only then compares that against your candidate. It returns a review delta.

What comes back is a second opinion, not a ruling. Verify each objection against the cited evidence: apply the ones the evidence supports, reject the ones it does not and record why, investigate the rest. You own the final artifact; codex-mcp never writes it.

The reviewer is strictly read-only: it cannot edit files, commit, push, modify issues, or write to any database or external system.

Required: reviewType, project.root, and a matching candidate set. Everything else — task context, blast-radius, test-charter, connectors — is optional and never blocks a review.

codex_auth_statusA

Report whether Codex is authenticated and which auth mode is in use.

Call this before a review if you want to fail fast with a clear message. Credentials are owned by the Codex CLI and the operating system; this never returns a token, API key, cookie, or any other secret.

Two auth modes are supported: chatgpt (browser sign-in to a ChatGPT subscription) and api (an OpenAI API key). The response reports the active mode, the configured mode, and whether they agree — reviews fail while they disagree.

If it reports authenticated: false, the user must run codex-mcp login in a terminal. That flow is interactive and cannot be triggered from here.

codex_capabilitiesA

Report what evidence this codex-mcp instance can actually reach, and what it is forbidden to do.

Diagnostic only — it runs no review and changes nothing. Use it to find out, before you rely on it, whether the requirement system or database is available for independent verification, and which downstream tools were withheld by policy.

Probing connectors takes a moment; pass probeConnectors: false for a configuration-only answer.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/salmansrabon/codex-mcp'

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