codex-mcp-tool
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_CLI_PATH | No | Path to the Codex CLI executable, e.g., /opt/homebrew/bin/codex | |
| CODEX_MAX_SESSIONS | No | Maximum number of sessions to keep (default: 50) | 50 |
| CODEX_SESSION_TTL_MS | No | Session time-to-live in milliseconds (default: 24h) | 24h |
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 | {} |
| logging | {} |
| prompts | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask-codexC | Execute Codex CLI with file analysis (@syntax), skills ($syntax), model selection, and safety controls. Supports changeMode. |
| batch-codexA | Delegate multiple atomic tasks to Codex for batch processing. Ideal for repetitive operations, mass refactoring, and automated code transformations |
| review-changesB | Run a code review against the current repository using Codex CLI native review subcommand |
| pingC | Echo |
| helpC | receive help information |
| versionA | Display version and system information |
| brainstormC | Generate creative ideas using structured frameworks with domain context and feasibility analysis. |
| fetch-chunkA | Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response. |
| list-sessionsB | List all active conversation sessions with metadata, or manage sessions |
| healthC | Check Codex CLI and session health status |
| list-skillsA | Discover available Codex skills: project .agents/skills and .codex/skills, plus user $CODEX_HOME/skills and ~/.agents/skills |
| do-actB | Execute task via Codex, verify with shell command, auto-fix on failure. Act-Check-Fix loop. |
| image-genA | Generate or edit images with Codex's built-in image_gen tool (ChatGPT login, no API key). Builds a structured prompt from use case, style, composition, exact text, reference roles and edit invariants, then returns the saved file paths. The image model and pixel size are chosen by Codex; aspect ratio and transparency are requested through the prompt. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ask-codex | Execute Codex CLI with optional changeMode |
| batch-codex | Execute multiple atomic Codex tasks in batch mode for efficient automation |
| review-changes | Execute Codex's built-in code review on current changes |
| ping | Echo test message with structured response. |
| help | receive help information |
| version | Get version information for Codex CLI and MCP server |
| brainstorm | Create structured brainstorming with chosen methodology and analysis |
| fetch-chunk | Fetch the next chunk of a response |
| list-sessions | View and manage active Codex sessions |
| health | Diagnose Codex CLI installation, authentication, and session health |
| list-skills | List available Codex skills in the current project |
| do-act | Execute task with verification-driven retry |
| image-gen | Generate or edit an image with Codex's built-in image_gen tool |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
ask-codex, do-act, batch-codex, and brainstorm all ultimately wrap the same Codex CLI execution, differentiated mainly by prompt framing and verification loops rather than distinct resources. review-changes is close to ask-codex as well, since a review is just a specialized Codex invocation. The descriptions do help separate single-task, batch, act-check-fix, and ideation modes, but an agent could easily pick the wrong wrapper.
All names use kebab-case, which is good, but the conventions are mixed: verb_noun (ask-codex, list-skills, review-changes, fetch-chunk), bare nouns/utilities (health, version, help, ping), and modifier_noun (image-gen, batch-codex). do-act is vague compared to its siblings, and ask-codex vs batch-codex vs do-act do not read as a coherent family.
13 tools is a well-scoped size for a CLI-wrapper server. A few slots are boilerplate (ping, help, version) rather than real capabilities, but overall each tool corresponds to a plausible use case.
Core execution paths are covered: single ask, batch, verified act, review, image generation, skills discovery, session listing, health, and chunk retrieval. However, sessions can only be listed/managed vaguely with no get/delete/detail tool, and there is no way to cancel or abort a long-running Codex run, which are common lifecycle gaps for this domain.