Skip to main content
Glama
aresyn

Codex Control Plane MCP

codex_submit_task

Queue a durable Codex write operation and return an operationId for tracking. Supports chat, execution, and thread operations with retry-safe submission.

Instructions

Queue a durable Codex write operation and return operationId immediately. For project-scoped work, pass project_id from codex_list_projects.projectId; project name or project path are accepted aliases and MCP stores the canonical projectId. Always pass client_request_id and poll codex_get_operation_status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operation_typeYes
client_request_idNoStable retry idempotency key. If omitted, MCP creates a new operation and relies on prompt deduplication to prevent active duplicate turns.
agent_idNoOptional orchestrator/agent id used by the central worker scheduler for per-agent limits.
resource_keysNoOptional write-scope keys. Disjoint keys allow parallel workspace-write/danger-full-access turns in the same project.
priorityNonormal
estimated_cost_classNonormal
thread_modeNoExplicit thread intent. Defaults to new_thread for start_chat and continue_thread for send_message/execute_plan.
dedup_policyNoControls prompt duplicate handling without changing client_request_id idempotency.
allow_historical_continuationNoOpt-in only. Allows fuzzy duplicate matching to continue a completed historical thread.
project_idNoProject reference for start_chat and other project-scoped operations. Prefer the canonical projectId returned by codex_list_projects; the listed project name or full project path are also accepted and canonicalized before durable writes.
chat_idNo
thread_idNoRequired for operation_type='steer_turn'. Target thread that owns the active turn.
source_thread_idNoRequired for operation_type='fork_thread'. Source thread to fork from.
expected_turn_idNoRequired for operation_type='steer_turn'. Active turn id precondition passed to Codex app-server.
workflow_idNo
messageNoRequired for all operation types except fork_thread. For fork_thread, omit it for fork-only or provide it to start the first turn in the forked thread.
input_itemsNoOptional image inputs appended to the text message for operation types that start a new turn. Supports image URL and localImage file path items only.
titleNo
cwdNo
modelNo
fork_configNo
ephemeralNo
output_schemaNoOptional JSON Schema passed to app-server outputSchema for this turn final assistant message.
collaboration_modeNo
approval_policyNoon-request
sandboxNoread-only
forceNo
timeout_secondsNo
first_message_max_charsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes
errorNo
agentGuidanceNo
agentGuidanceTextNo
recoveryAttemptStateNo
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It states the operation is durable and returns immediately, and mentions idempotency via client_request_id. It does not discuss potential side effects, rate limits, or failure behavior, which is a gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, efficiently front-loading the core action and key usage notes without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 29 parameters and many siblings, the description is too brief. It does not explain how to choose operation types, the meaning of many parameters, or the overall workflow, leaving much to the schema and agent's interpretation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 45%, so many parameters are already documented. The description adds value by highlighting client_request_id and project_id importance, but does not elaborate on most other parameters beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queues a durable write operation and returns an operationId. It mentions the return behavior and project-scoped work, but does not clearly differentiate from sibling tools like codex_start_chat or codex_send_message, which may be specific operation types.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance: pass project_id for project-scoped work, always provide client_request_id, and poll codex_get_operation_status. However, it does not mention when not to use this tool or list alternatives for specific use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/aresyn/codex-control-plane-mcp'

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