B
Emerging
89/100
2 hours ago

codex-mcp-bridge

MCP server for Claude Desktop to send prompts into a live Codex thread through a shared Codex app-server, preserving thread history, working directory, and model.

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored

Monitored 0 days · every push re-verified

Who stands behind it

gmail.com (@buidangminh23) · Ownership Verified

Source: Glama

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
7 tools verified — handlers match their declared behaviour
5 read-only tools verified — handlers contain no write/delete/exec
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
Are you the publisher? Confirm or correct these findings.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCLAUDE_BRIDGE_CWDthe process cwd The working directory the peer advertises.
configCLAUDE_BRIDGE_PEER_NAMEcodex mcp add claude-bridge --env =codex-desktop -- "$(command -v node)" "$PWD/src/claude-bridge.mjs"
configCODEX_APP_SERVER_URL"": "ws://127.0.0.1:8791"
configCODEX_BIN"": "/Users/<user>/.local/bin/codex",
configCODEX_BRIDGE_APPROVALdeny How to answer approval requests from Codex. approve is ignored unless CODEX_BRIDGE_AUTO_APPROVE_ACK=1 is also set.
configCODEX_BRIDGE_AUTOSTART1 0 = never spawn an app-server; one must already be running.
configCODEX_BRIDGE_AUTO_APPROVE_ACKCODEX_BRIDGE_APPROVAL deny How to answer approval requests from Codex. approve is ignored unless =1 is also set.
configCODEX_BRIDGE_EFFORTCODEX_BRIDGE_MODEL=gpt-5.6-luna =xhigh node scripts/install-claude-desktop.mjs
configCODEX_BRIDGE_MODELgpt-5.6-luna CODEX_BRIDGE_EFFORT=xhigh node scripts/install-claude-desktop.mjs
configCODEX_BRIDGE_REMAP1 0 disables cwd remapping between a shared drive and a local checkout.
configCODEX_BRIDGE_WORKSPACE_ROOTS$HOME and the bridge's parent directory Where to look for a project by name, most preferred first, separated by : (; on Windows). Setting it replaces the derived roots rather than adding to them.
configCODEX_THREAD_ID
configProgramFilesWindows %LOCALAPPDATA%\Programs\OpenAI\Codex\bin\codex.exe → %APPDATA%\npm\codex.cmd → %%\nodejs\codex.cmd
configXDG_CONFIG_HOMELinux ${:-~/.config}/Claude/claude_desktop_config.json
// quality suggestions

All four hints declared on every tool

5/14 tools missing one or more hints — list_codex_threads (missing: destructiveHint, idempotentHint); read_codex_thread (missing: destructiveHint, idempotentHint); codex_bridge_status (missing: destructiveHint, idempotentHint), +2 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Shell command execution

4 child_process/subprocess calls in production code — runs shell commands (src/app-server-client.mjs:79, src/app-server-client.mjs:106, src/peer-protocol.mjs:55)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/buidangminh23-codex-mcp-bridge-1ke8t1)](https://m8ven.ai/mcp/buidangminh23-codex-mcp-bridge-1ke8t1)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 8038a1fb6e4da6b5a1bc9ac6dc57f3b787c4b97a
code hash: b8a82a9d7ae7666d4ea4e74784a5f9b94b35934899a7913de2388ffacce42970
verified: 8/19/2026, 3:53:54 PM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client