claude-ask
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@claude-askanalyze the performance of the main query in database.py"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Claude Ask
Claude Ask is an open-source Codex plugin that runs a locally authenticated Claude Code Sonnet 5, Fable, or Opus model as an independent second opinion or full autonomous coding agent.
It provides five persistent asynchronous MCP tools:
askstarts a new advisory or workspace-agent job;ask_followupresumes a completed Claude session and forks a new branch;ask_statuswaits for progress or returns the final result;list_jobslists recent jobs and recovers lost IDs;cancel_askexplicitly cancels a job and its process tree.
Jobs support a human-readable name, medium | high | xhigh | max effort
(high by default), and an optional max_budget_usd ceiling.
Install in Codex
Add this Git repository as a marketplace and install the plugin:
codex plugin marketplace add AbsoluteMode/claude-ask
codex plugin add claude-ask@absolutmodeStart a new Codex task after installing or updating so the skill and MCP tool schemas are reloaded.
Related MCP server: codemcp
Requirements
Codex with plugin support;
Node.js 22 or newer;
Claude Code on
PATHor at~/.local/bin/claude;an authenticated Claude Code session.
Access modes
Without workspace, Claude receives only the supplied question and runs in
safe mode with no tools.
With an explicit absolute workspace, Claude runs as a full-access coding
agent. Its default tools, shell, file editing, user/project instructions and
hooks, network access, and configured MCP servers, skills, and plugins remain
available. Interactive permission checks are bypassed because the detached
process cannot answer prompts.
The workspace is Claude's working directory and intended task scope, not a hard operating-system sandbox. Only pass trusted workspaces and prompts.
Reliability and privacy
Prompts travel over stdin, never argv, environment variables, state, or logs.
Job directories use mode
0700; private files use mode0600.Jobs survive MCP server restarts and remain discoverable through
list_jobs.Boot-aware recovery avoids trusting reused PIDs after a machine restart.
Cancellation terminates Claude's POSIX process group with
SIGTERM → SIGKILL.Stderr is capped at 1 MiB; failures expose at most a 4 KiB diagnostic tail.
There is no automatic elapsed-time or idle-time cancellation.
Completed plugin job data is retained for 24 hours by default; resumable Claude sessions use Claude Code's normal session storage.
See the plugin documentation for the complete protocol and configuration reference.
Development
npm test
npm run checkThe default suite uses a fake Claude executable and consumes no model usage. An authenticated paid/limited-usage smoke test is explicit:
npm run test:liveLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Paid remote MCP for Claude Code skill update gate MCP, structured receipts, audit logs, and reviewer
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
Multi-model code review: a panel of models + detectors return a pass/fail verdict. Paid via x402.
A paid remote MCP for CodeG, built to return verdicts, receipts, usage logs, and audit-ready JSON.
Related MCP Servers
- AlicenseAqualityDmaintenanceWraps Claude Code as tools for MCP clients, enabling autonomous coding tasks via a 4-tool lifecycle with session management, async polling, and permission controls.434 npm20MIT
- AlicenseNot gradedqualityBmaintenanceForwards normalized MCP tools to Codex or Claude Code for agentic coding tasks like starting new sessions, continuing existing ones, and checking status.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables any MCP client to request an independent second opinion from a fresh Claude Code session without blocking, useful for plans, architecture, debugging, security reviews, and final checks.5 npmMIT
- AlicenseAqualityAmaintenanceEnables compatible MCP clients to invoke Kimi Code for second opinions, code reviews, and delegated coding tasks with structured results.16MIT