Schema | Orchestrate Codex

Orchestrate Codex

Describes the environment variables required to run the server.

Name	Required	Description	Default
No arguments

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`	{}

Functions exposed to the LLM to take actions

Name	Description
orchestrate_list_recipesA	List built-in supervised orchestration recipes.
orchestrate_explain_recipeC	Explain a recipe: stages, doc_class, context policy, default leaf bindings.
orchestrate_context_policyB	Return context policy for a doc_class (durable\|change\|transform\|direct).
orchestrate_plan_recipeC	Build a static plan (steps + suggested tools). Prefer start_run for stateful execution.
orchestrate_start_runC	Start a supervised run. Auto-executes local gather stages. Returns next_action (call_tool with leaf name+args, or done). Does not call other MCP servers — Codex must invoke the leaf tool.
orchestrate_continue_recipeA	Advance a run after a leaf tool result. Pass run_id and/or full state. On leaf failure set success=false to try fallback_tools (Claude→Grok→AG).
orchestrate_get_runA	Fetch run state by run_id (same process only).
orchestrate_fallback_chainsC	Show default capability→fallback leaf tool chains.

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/Meapri/orchestrate-codex'

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