Skip to main content
Glama
buidangminh23

codex-mcp-bridge

by buidangminh23
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
JavaScript
Local

Start a new Codex thread

start_codex_thread
Destructive

Start a new Codex session in a given directory, providing an optional prompt, title, and model to begin the task immediately.

Instructions

Start a Codex task. In Desktop mode include the initial prompt to create and assign a visible task atomically; use delegate_to_codex to also wait for its reply.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdYesAbsolute working directory for the new Codex session
nameNoOptional title to show for the new Codex session
modelNoModel override, e.g. gpt-5.6-luna
promptNoInitial task; required with CODEX_BRIDGE_DESKTOP_TASKS=1, starts immediately

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / prompt
      Added value: +{
+  "description": "Initial task; required with CODEX_BRIDGE_DESKTOP_TASKS=1, starts immediately",
+  "minLength": 1,
+  "type": "string"
+}
  2. First observedv1.11.2

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false. The description adds useful behavioral context by mentioning atomic task creation, visible task assignment, and the fact that this tool does not wait for the reply, which is a meaningful behavioral distinction from its sibling.

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?

Two short sentences deliver the core purpose and the most important usage distinction without filler. The main action is front-loaded, and the sibling routing guidance is efficiently integrated.

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

Completeness4/5

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

For a tool with a straightforward purpose, the description plus rich schema and annotations provide enough context to invoke it correctly. It does not describe the return value or non-Desktop mode behavior explicitly, but the sibling list and schema fill most practical gaps.

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 coverage is 100%, so the schema already documents each parameter including cwd, name, model, and prompt. The description adds only a small amount of context tying the prompt to Desktop-mode task creation, but it does not meaningfully expand on the schema's own parameter descriptions.

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 clearly states the tool 'Start a Codex task' with a specific verb and resource, and the title reinforces that it creates a new thread. It also distinguishes itself from delegate_to_codex by noting that the delegate variant additionally waits for the reply.

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 context for Desktop mode, telling the agent to include the initial prompt when creating a visible task atomically. It also names delegate_to_codex as the alternative when waiting for a reply, though it does not enumerate all other sibling alternatives or explicitly state non-Desktop mode behavior.

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