Schema | Codex Gemini MCP

Codex Gemini MCP

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_LOG_DIR`	No	Log path override.
`MCP_LOG_PREVIEW`	No	Whether to save log previews. Set to '1' to enable.
`MCP_RUNTIME_DIR`	No	Default runtime file root (e.g., .codex-gemini-mcp).	.codex-gemini-mcp
`MCP_LOG_FULL_TEXT`	No	Whether to save full text logs. Set to '1' to enable.
`MCP_CLI_TIMEOUT_MS`	No	Default CLI timeout in milliseconds. Default is 600000 (10 minutes).	600000
`MCP_MAX_OUTPUT_BYTES`	No	Maximum output bytes (cap, for future runtime extension).
`MCP_CODEX_DEFAULT_MODEL`	No	Default model for codex. Default is gpt-5.3-codex.	gpt-5.3-codex
`MCP_GEMINI_DEFAULT_MODEL`	No	Default model for gemini. Default is gemini-3-pro-preview.	gemini-3-pro-preview

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
ask_codexC	Send a prompt to local Codex CLI and return its output.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/donghae0414/codex-gemini-mcp'

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