codex-claude-subagent (zetsubo-dev/codex-claude-subagent) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 11 tools. No publisher has claimed this listing.

C
Caution
74/100
1 month ago

codex-claude-subagent

Enables Codex to delegate tasks to interactive Claude Code sessions as role-controlled subagents for exploration, code review, and implementation, using the existing Claude Code installation on macOS.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

zetsubo-dev

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

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

// key findings
⚠️
Tool descriptions don’t match what handlers do
4 tools describe read intent but their handlers mutate — claude_interactive_read (line 395: fs.writeFileSync(tmpPath, payload, { mode: PRIVATE_FILE_MODE })); claude_interactive_read_log (line 395: fs.writeFileSync(tmpPath, payload, { mode: PRIVATE_FILE_MODE })); claude_interactive_list (line 297: fs.mkdirSync(STATE_DIR, { recursive: true, mode: PRIVATE_DIR_MODE }))
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.
// 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.
configCODEX_CLAUDE_SUBAGENT_RELEASE_DIR
configCODEX_CLAUDE_SUBAGENT_REQUEST_WAIT_SCHEDULE_MS
configCODEX_CLAUDE_SUBAGENT_RUN_LIVE
configCODEX_CLAUDE_SUBAGENT_STATE_DIR
configTERM
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

11/11 tools missing one or more hints — claude_interactive_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); claude_interactive_send (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); claude_interactive_request (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 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.

Descriptions match behaviour

4 tools describe read intent but their handlers mutate — claude_interactive_read (line 395: fs.writeFileSync(tmpPath, payload, { mode: PRIVATE_FILE_MODE })); claude_interactive_read_log (line 395: fs.writeFileSync(tmpPath, payload, { mode: PRIVATE_FILE_MODE })); claude_interactive_list (line 297: fs.mkdirSync(STATE_DIR, { recursive: true, mode: PRIVATE_DIR_MODE }))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

9/11 tool handlers declare input schemas (82%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

10/11 tool handlers wrap calls in try/catch (91%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

1 child_process call — runs shell commands

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

Tool description accuracy

5 tools have description/behavior mismatches: claude_interactive_start: description implies read-only but handler writes/deletes/executes; claude_interactive_read: description implies read-only but handler writes/deletes/executes; claude_interactive_read_log: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 8 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/zetsubo-dev/codex-claude-subagent?variant=verified)](https://m8ven.ai/mcp/zetsubo-dev/codex-claude-subagent)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: e4bd1d8cc58fe8daf44547d10e851f46d5cb57d2
code hash: d8f69a20a1319dd8a31b5b1e4e2ce56edebfa4fa539d33b1794fe517d23ba1be
verified: 8/2/2026, 8:58:58 AM
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