claude-ask
Enables users to request a second opinion from a locally authenticated Claude Code model via MCP tools, supporting asynchronous jobs with restricted tools for safety.
README
Claude Ask
Claude Ask is an open-source Codex plugin that asks a locally authenticated Claude Code model for an independent second opinion.
It provides three MCP tools:
askstarts a persistent asynchronous Claude Fable or Opus job;ask_statusreports progress and returns the final answer;cancel_askexplicitly cancels a job.
For repository reviews, ask accepts an explicit absolute workspace. Claude
runs from that directory with only the built-in Read, Glob, and Grep
tools. It cannot run shell commands or edit files. Without workspace, Claude
receives no tools.
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@absolutmode
Start a new Codex thread after installation so the new skill and MCP tool schema are loaded.
Requirements
- Codex with plugin support;
- Node.js 22 or newer;
- Claude Code installed at
~/.local/bin/claude, orCLAUDE_ASK_CLIset to another executable; - an authenticated Claude Code session.
Security model
- The prompt is transferred over stdin, never argv or environment variables.
- Job directories use mode
0700; job files use0600. - Workspace access is explicit per job and canonicalized before launch.
- Workspace jobs expose only
Read,Glob, andGrep. - There is no automatic elapsed-time or idle timeout.
- Jobs survive an MCP server restart and are retained for 24 hours by default.
- At most four jobs run concurrently by default.
See the plugin documentation for protocol and configuration details.
Development
npm test
The default test uses a fake Claude executable and consumes no model usage. An explicit live smoke test is available after Claude authentication:
npm run test:live
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.