Schema | codex-mcp-longrun

codex-mcp-longrun

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LONGRUN_STATE_DIR`	No	Directory for job logs and metadata. Defaults to ~/.local/state/codex-longrun.	~/.local/state/codex-longrun
`LONGRUN_ALLOWED_ROOTS`	Yes	Trusted project directory or colon-separated list of directories. The server validates the resolved working directory against these allowed roots.
`LONGRUN_HEARTBEAT_INITIAL_SEC`	No	Delay before the first heartbeat notification. 0 disables heartbeats.	300
`LONGRUN_HEARTBEAT_INTERVAL_SEC`	No	Interval between later heartbeat notifications.	900

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": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
health	Return server paths, versions, and configured guardrails.
run_and_wait	Run one approved non-interactive process and return one bounded terminal result.
read_log_tail	Read only the bounded tail stored for a known job ID.

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/woffko/codex-mcp-longrun'

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