Codex Control Plane MCP

Overview Schema Source Related Servers Discussions Admin

codex_start_chat

Starts a new Codex chat synchronously for a given project and initial message. Prefer codex_submit_task for durable long-running tasks.

Instructions

Compatibility write for starting a new Codex chat. Prefer codex_submit_task with operation_type='start_chat' for durable long work. In client mode this delegates to the durable queue.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "message": "<message>"
    },
    "name": "codex_start_chat"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	Yes
`message`	Yes
`title`	No
`cwd`	No
`model`	No
`sandbox`	No		read-only
`approval_policy`	No		on-request
`collaboration_mode`	No
`timeout_seconds`	No
`first_message_timeout_seconds`	No	Deprecated and ignored. This tool now returns immediately after turn/start; use codex_get_turn_status for messages.
`first_message_max_chars`	No

Output Schema

Name	Required	Description	Default
`ok`	Yes
`error`	No
`agentGuidance`	No
`agentGuidanceText`	No
`recoveryAttemptState`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedJun 19, 2026
- addedOutput schema / properties / agentGuidance
```
Added value: +{
+  "additionalProperties": true,
+  "type": "object"
+}
```
- addedOutput schema / properties / agentGuidanceText
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / recoveryAttemptState
```
Added value: +{
+  "additionalProperties": true,
+  "type": "object"
+}
```
First observedv0.1.2Jun 18, 2026

TDQS

B3.3/5.0

Behavior2/5

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

No annotations provided; description only mentions 'compatibility write' and delegation. Lacks details about side effects, return behavior, idempotency, or mutation scope. The parameter description (in schema) reveals that tool returns immediately, but this is not in the main description. Insufficient disclosure for a write tool.

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

Conciseness4/5

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

Description is three sentences, no fluff, and front-loaded with purpose and usage guidance. However, it sacrifices necessary detail for brevity. Still, it is appropriately concise.

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

Completeness1/5

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

Given 11 parameters, no annotations, and many siblings, the description is grossly incomplete. It does not explain parameters, output schema, error conditions, or lifecycle. A tool of this complexity requires far more context.

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

Parameters1/5

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

Schema description coverage is only 9%; most parameters have no description. The tool description adds no parameter meaning—it doesn't explain any of the 11 parameters, their defaults, or relationships. Fails to compensate for low schema coverage.

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

Purpose5/5

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

Description clearly states tool is for starting a new Codex chat ('Compatibility write for starting a new Codex chat'). It distinguishes itself from codex_submit_task, which is preferred for durable long work, and mentions delegation behavior in client mode. This differentiates it clearly from siblings.

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

Usage Guidelines5/5

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

Explicit guidance to prefer codex_submit_task with operation_type='start_chat' for durable long work, and notes that in client mode it delegates to durable queue. This tells the agent when not to use this tool and suggests an alternative.

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

Deploy Server