Codex Control Plane MCP

Overview Schema Source Related Servers Discussions Admin

codex_restart_app_server

Restart the codex-app-server subprocess when guidance recommends it, only after ensuring no active work is present. Delegates to worker lane in client mode.

Instructions

Restart only the MCP-owned codex-app-server subprocess. Use this only when guidance recommends restart and active work is absent or explicitly handled. In client mode this delegates to the worker command lane.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "codex_restart_app_server"
  }
}

Input Schema

Name	Required	Description	Default
`start_after_restart`	No
`timeout_seconds`	No
`force`	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

A3.8/5.0

Behavior3/5

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

The description reveals that in client mode the action is delegated to the worker command lane, and implies that active work should be absent, indicating potential disruption. However, it does not explain other behavioral traits such as whether the restart is graceful, what happens to app state, or authorization requirements. With empty annotations, more transparency would be beneficial.

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 concise at three sentences, immediately stating the core purpose ('Restart only the MCP-owned codex-app-server subprocess'), then providing usage and behavioral context. Every sentence adds value without redundancy.

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

Completeness3/5

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

The description covers the primary purpose, usage conditions, and a special behavioral note for client mode. However, it lacks details on parameter semantics, return values (though output schema exists but is not described), and safety considerations beyond the active-work caveat. Given the tool's moderate complexity (3 optional parameters) and no annotations, the description is partially complete but leaves important questions unanswered.

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?

The input schema has three parameters (start_after_restart, timeout_seconds, force) with no descriptions (0% coverage). The tool description does not explain or expand on any of these parameters, leaving the agent without guidance on their purpose or impact. This is a significant gap for a tool with optional parameters.

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?

The description explicitly states the action (restart) and the target (MCP-owned codex-app-server subprocess), which is a specific verb+resource combination. It distinguishes from related tools like codex_get_app_server_status by focusing on restarting the subprocess, a unique operation among 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?

The description provides explicit when-to-use guidance: only when guidance recommends restart and active work is absent or handled. It also notes behavior differences in client mode, helping the agent understand context. No alternative is mentioned, but no alternative exists among siblings, so it's sufficient.

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

Deploy Server