CodexMCP
by tomascupr
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_PATH | No | Path to Codex CLI executable if not in PATH. | |
| OPENAI_API_KEY | Yes | Your OpenAI API key (required). | |
| CODEXMCP_USE_CLI | No | Whether to use Codex CLI when available. | true |
| CODEXMCP_CACHE_TTL | No | Cache time-to-live in seconds. | 3600 |
| CODEXMCP_LOG_LEVEL | No | Logging level. | INFO |
| CODEXMCP_CONSOLE_LOG | No | Enable console logging. | true |
| CODEXMCP_MAX_RETRIES | No | Maximum retry attempts for API calls. | 3 |
| CODEXMCP_CACHE_ENABLED | No | Enable response caching. | true |
| CODEXMCP_DEFAULT_MODEL | No | Default model to use. | o4-mini |
| CODEXMCP_RETRY_BACKOFF | No | Exponential backoff factor for retries. | 2.0 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
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/tomascupr/codexMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server