Skip to main content
Glama

codex-bridge

Give Claude Code a Codex sparring partner.

codex-bridge is an MCP server that lets Claude Code ask GPT Codex for adversarial planning, code review, debugging, research, and risk triage without leaving your project workflow.

The npm package is @ndcorder/codex-bridge. The installed CLI binary and MCP server key are both codex-bridge.

What It Does

  • codex_plan: get an implementation plan with trade-offs and stop-ship checks before writing code.

  • codex_review: ask Codex for critical code review, with evidence mode on by default.

  • codex_ask: brainstorm, sanity-check assumptions, or compare approaches.

  • codex_risk_radar: score a diff and choose the right collaboration depth.

  • codex_research: run multi-turn research and write durable research artifacts.

  • codex_debug: run structured root-cause analysis for hard bugs.

  • codex_stats, codex_sessions, codex_reset: inspect and manage bridge sessions.

Related MCP server: codex-dobby-mcp

Requirements

  • Node.js 20 or newer is recommended. CI runs on Node 20 and 22.

  • The Codex CLI must be installed, authenticated, and available as codex on PATH.

  • An MCP-capable client such as Claude Code.

Check the Codex CLI before configuring the bridge:

codex --version

Quick Start

From the project where you want Claude Code to use Codex:

npx -y @ndcorder/codex-bridge init

This command:

  • creates or updates .mcp.json with a codex-bridge stdio server entry

  • preserves existing MCP servers

  • appends Codex Bridge guidance to CLAUDE.md if it is not already present

Restart Claude Code after running the init command.

Manual MCP Configuration

If you prefer to edit MCP config yourself, add this server entry:

{
  "mcpServers": {
    "codex-bridge": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@ndcorder/codex-bridge"]
    }
  }
}

First Workflows

Ask Codex to plan before a risky change:

Use codex_plan to review this approach before implementation:
<describe the feature, constraints, and files involved>

Ask for evidence-based review after changes:

Use codex_review with include_diff=true and evidence_mode=true.
Focus on security, data loss, and API regressions.

Use risk radar when deciding how much review a diff needs:

Use codex_risk_radar on the current diff and recommend whether to ask,
review, or plan then review.

See docs/USAGE.md for more workflows.

Configuration

Environment variables:

  • CODEX_BRIDGE_MODEL or CODEX_MODEL: default model override. Default: gpt-5.3-codex.

  • CODEX_BRIDGE_RETRIES: transient retry count. Default: 1.

  • CODEX_BRIDGE_RETRY_BACKOFF_MS: retry backoff base in milliseconds. Default: 500.

  • CODEX_BRIDGE_MAX_SESSIONS: max in-memory sessions before oldest-session eviction. Default: 200.

  • CODEX_BRIDGE_SESSION_TTL_MS: session inactivity TTL in milliseconds. Default: 86400000.

Common per-request runtime options:

  • working_dir: project directory for Codex file access and implicit session key.

  • timeout: timeout in milliseconds, max 600000.

  • session_id: explicit context isolation key.

  • model: per-request Codex model override.

  • retries: per-request retry count, max 10.

  • retry_backoff_ms: per-request retry backoff base, max 60000.

Full tool schemas are in docs/TOOLS.md.

Documentation

Local Development

npm install
npm run build
npm test

Run the full verification suite:

npm run verify

The full suite includes unit tests, the MCP stdio smoke test, and the bake-off black-box suite.

Release Commands

  • npm run release:bump: bump patch version in package.json and package-lock.json.

  • npm run release:bump:patch|minor|major: explicit semver bump.

  • npm run release:notes: generate .release/RELEASE_NOTES.md from CHANGELOG.md.

  • npm run release:pack-check: build and run npm pack --dry-run.

  • npm run release:prepare: run verify, pack check, and release notes generation.

Publish scoped packages publicly with:

npm publish --access public

Package Contents

The npm package intentionally ships only runtime output and documentation:

  • dist/src

  • README.md

  • CHANGELOG.md

  • docs/*.md

Generated research artifacts are written to the consuming project's .codex-bridge/ directory when codex_research receives working_dir.

Available Tools

9 tools
codex_askA

Ask GPT Codex a question or brainstorm an idea. Codex acts as a critical thinking partner — it will challenge assumptions and surface risks.

Inputs: prompt (required), context, working_dir, timeout, +4 more.

codex_debugA

Structured root-cause analysis via GPT Codex. Multi-turn: Codex generates hypotheses, tests them against the code and web sources, then delivers a verdict with evidence chain. Can take minutes. Use for hard-to-find bugs, unexpected behavior, or production incidents.

Inputs: symptoms (required), code, context, max_turns, +6 more.

codex_planA

Collaboratively plan an implementation with GPT Codex. Describe the problem and constraints, get a concrete approach with trade-offs and alternatives.

Inputs: problem (required), constraints, working_dir, timeout, +4 more.

codex_researchA

Deep-dive research via GPT Codex. Multi-turn: Codex surveys the topic, drills into gaps, then synthesizes findings. Can take minutes — trades speed for depth. Use for architecture exploration, library evaluation, or understanding unfamiliar codebases.

Inputs: topic (required), context, max_turns, working_dir, +5 more.

codex_resetA

Reset the conversation session with Codex. Clears history and stats. Use when starting a new topic.

Inputs: session_id, working_dir, all_sessions.

codex_reviewA

Send code to GPT Codex for critical review. Codex will look for bugs, security issues, performance problems, and design flaws.

Inputs: code (required), description, include_diff, evidence_mode, +6 more.

codex_risk_radarA

Analyze a git diff to identify risk zones and recommend the right collaboration depth. Returns risk score, affected categories, and whether to use codex_ask, codex_review, or codex_plan+review.

Inputs: diff (required), changed_files, commit_message, working_dir, +1 more.

codex_sessionsA

List active in-memory sessions with recency and activity summary. Useful when running multiple clients against one bridge process.

Inputs: limit.

codex_statsA

Get round-trip statistics for this session's Claude ↔ Codex collaboration. Shows number of exchanges, latency breakdown, and per-tool usage.

Inputs: session_id, working_dir.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool targets a distinct interaction mode with Codex: brainstorming, debugging, planning, deep research, session reset, code review, risk analysis of diffs, session listing, and statistics. No overlap in purpose.

    Naming Consistency5/5

    All tools follow a consistent 'codex_' prefix with a descriptive verb or noun in snake_case (e.g., codex_ask, codex_research, codex_risk_radar). The pattern is uniform and predictable.

    Tool Count5/5

    With 9 tools, the set is well-scoped for its purpose. Each tool serves a clear function without redundancy, fitting the typical optimal range of 3–15 tools.

    Completeness4/5

    The set covers major interaction types with Codex (ask, debug, plan, research, review, risk analysis) along with session management and stats. A minor gap is the absence of a direct 'codex_edit' or 'codex_refactor' tool, but core workflows are well-supported.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      A local MCP server that lets Claude delegate scoped work to Codex with structured results and guardrails, supporting planning, code review, build, reverse engineering, and long-running background tasks.
      11
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server enabling Claude to consult Codex (GPT-5.x) mid-task for second opinions, plan/diff review, brainstorming, and codebase exploration via structured debates and permission-controlled interactions.
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A MCP server that enables Claude Code to delegate coding tasks to Codex via the MCP protocol, with task management, security checks, and result verification.
      42 npm
      MIT