codex-mcp
Enables Claude Code to call OpenAI Codex for read-only design, deep reasoning, and code review tasks.
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
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
sam-mountainman
Source: Glama
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
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
gpt_statusCheck the local Codex CLI, authentication, configured defaults, and model catalog without calling a model or spending usage.
gpt_planAsk an OpenAI Codex model to inspect a repository read-only and produce a concrete implementation plan. Model and reasoning effort can be selected per call.
gpt_askAsk an OpenAI Codex model for deep reasoning, debugging hypotheses, trade-off analysis, or a second opinion. It may inspect the repository read-only.
gpt_reviewAsk an OpenAI Codex model to review the current implementation read-only. It inspects the working tree and prioritizes correctness, security, regressions, and missing tests.
gpt_continueContinue a previous codex-mcp conversation using its session_id. The model and reasoning effort may be changed for the resumed turn.
CLAUDE_PROJECT_DIRCODEX_MCP_CODEX_BINCodex CLIの絶対パスCODEX_MCP_DEFAULT_MODELCODEX_MCP_DEFAULT_REASONING_EFFORTTool 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
5/5 tools missing one or more hints — gpt_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gpt_plan (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gpt_ask (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +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.
Descriptions match behaviour
4 tools describe read intent but their handlers mutate — gpt_status (line 346: spawnSync(CODEX_BIN, args, {); gpt_plan (line 210: spawn(codexBin, args, {); gpt_ask (line 210: spawn(codexBin, args, {)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
4/5 tool handlers declare input schemas (80%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
Only 0/5 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Tool description accuracy
3 tools have description/behavior mismatches: gpt_status: description implies read-only but handler writes/deletes/executes; gpt_ask: description implies read-only but handler writes/deletes/executes; gpt_review: 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.
[](https://m8ven.ai/mcp/sam-mountainman/codex-mcp)?variant=verified from the URL.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