codex-local-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_BIN | No | Absolute path to the Codex CLI. | codex |
| CODEX_MODEL | No | Model override. | |
| CODEX_MCP_ROOT | No | Root for all workspaces. Nothing is written outside it. | ~/.codex-mcp/workspaces |
| CODEX_TIMEOUT_SEC | No | Default timeout before a run is killed. | 300 |
| CODEX_NETWORK_ACCESS | No | Set false to deny Codex the network. | true |
| CODEX_MAX_TIMEOUT_SEC | No | Ceiling a caller may request. | 1800 |
| CODEX_MAX_OUTPUT_CHARS | No | Output cap; the head and tail are kept. | 40000 |
| CODEX_MAX_REPORTED_FILES | No | Cap on reported changed files. | 200 |
| CODEX_MAX_INLINE_IMAGE_BYTES | No | Above this, a downscaled preview is inlined instead. | 1048576 |
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 | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| codex_runA | Hand a natural-language task to the local Codex CLI coding agent. Codex can write and run code, install packages and call APIs inside an isolated workspace folder, then this returns its output plus any files it created. Blocking: it does not return until Codex finishes. |
| codex_generate_imageA | Generate images with the local Codex CLI. The prompt is passed through as written. Returns the saved file paths and shows the images inline, downscaling a preview when a file is too large to inline. Defaults to a fast low-quality 1024x1024 draft; raise quality for final assets. |
| codex_read_artifactA | Read one file from a Codex workspace, for artifacts that were too large to inline. Images come back as image content, everything else as text. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The three tools are largely distinct: one executes a coding agent, one reads artifact files, and one generates images. The only minor ambiguity is that codex_run's general-purpose mandate could conceptually cover image generation, but the dedicated image tool helps agents choose correctly.
All tools share a codex_ prefix and verb-first names (run, read_artifact, generate_image), which is a clear and predictable pattern. codex_run is slightly less descriptive because it omits a noun object, but it does not break the style badly enough to warrant a lower score.
Three tools is appropriate for a narrow local-Codex wrapper: each tool covers a distinct operation and none feels redundant or missing. The count is well within the ideal 3-15 range for a focused MCP server.
The server covers the core workflow of running a Codex task, inspecting generated artifacts, and generating images. Minor gaps remain, such as no explicit workspace listing, cancellation, or status operations, but agents can accomplish the primary goals with this surface.