codex-code-review
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@codex-code-review Can you review my uncommitted changes?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Codex MCP Code Review
Run Codex app-server reviews of uncommitted changes via an MCP tool. Compared to the built-in /review, this keeps review context clean while fixes happen in the main session that retains implementation knowledge, reducing regressions and enabling longer autonomous runs with better code quality.
Requirements
Codex CLI installed and authenticated.
uv installed.
Related MCP server: codex
Configure Codex (MCP)
Codex loads MCP servers from ~/.codex/config.toml and supports configuring them via the codex mcp CLI.
Review profile (recommended)
Profile example (gpt-5.5, medium reasoning effort):
# ~/.codex/config.toml
[profiles.review]
model = "gpt-5.5"
model_reasoning_effort = "medium"When the MCP server is started with --profile review, it reads this profile from
Codex config and applies supported review settings itself. Supported profile keys
are model, model_provider, service_tier, model_reasoning_effort, and
model_reasoning_summary.
AGENTS.md example instruction:
for verification call `review_uncommitted_changes: runs=1` until no issuesTool timeout (required)
Set tool_timeout_sec for the MCP server in ~/.codex/config.toml to a value larger than the review timeout (--timeout-seconds passed to the server command). Example: if the review timeout is 2700 seconds, set tool_timeout_sec = 3000.
Option A: CLI (recommended)
This registers a stdio MCP server that Codex launches when a session starts.
codex mcp add codex-code-review -- \
uv run -m mcp_code_review.server --parallelism 1 --concurrency-mode auto --timeout-seconds 2700 \
--profile reviewThe codex mcp add workflow is the supported way to add MCP servers from the CLI. After adding the server, set tool_timeout_sec in ~/.codex/config.toml (see Option B) so it is higher than --timeout-seconds.
Additional review instructions are enabled by default. Existing configurations that include
--enable additional_review_instructions still work for backward compatibility.
To disable additional review instructions, add:
--disable additional_review_instructionsOption B: config.toml
Add an MCP server entry in ~/.codex/config.toml:
[mcp_servers.codex-code-review]
command = "uv"
tool_timeout_sec = 3000
args = [
"run",
"-m",
"mcp_code_review.server",
"--parallelism",
"1",
"--concurrency-mode",
"auto",
"--timeout-seconds",
"2700",
"--profile",
"review"
]Codex reads MCP server entries from the mcp_servers table in ~/.codex/config.toml.
Configure with uvx (run directly from Git)
If you prefer not to clone locally, you can run the server directly from the Git repository using uvx.
Repository: https://github.com/Szpadel/codex-mcp-code-review
Codex (CLI)
codex mcp add codex-code-review-uvx -- \
uvx --from git+https://github.com/Szpadel/codex-mcp-code-review \
python -m mcp_code_review.server --parallelism 1 --concurrency-mode auto --timeout-seconds 2700 \
--profile reviewCodex (config.toml)
[mcp_servers.codex-code-review-uvx]
command = "uvx"
tool_timeout_sec = 3000
args = [
"--from",
"git+https://github.com/Szpadel/codex-mcp-code-review",
"python",
"-m",
"mcp_code_review.server",
"--parallelism",
"1",
"--concurrency-mode",
"auto",
"--timeout-seconds",
"2700",
"--profile",
"review"
]Claude Code (.mcp.json)
{
"mcpServers": {
"codex-code-review-uvx": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Szpadel/codex-mcp-code-review",
"python",
"-m",
"mcp_code_review.server",
"--parallelism",
"1",
"--concurrency-mode",
"auto",
"--timeout-seconds",
"2700",
"--profile",
"review"
],
"env": {}
}
}
}Developer mode (run from source path)
If you want Codex to run the server directly from this source checkout, point uv at the project path.
CLI
codex mcp add codex-code-review-dev -- \
uv run --project /absolute/path/to/codex-mcp-code-review -m mcp_code_review.server \
--parallelism 1 --concurrency-mode auto --timeout-seconds 2700 --profile reviewconfig.toml
[mcp_servers.codex-code-review-dev]
command = "uv"
tool_timeout_sec = 3000
args = [
"run",
"--project",
"/absolute/path/to/codex-mcp-code-review",
"-m",
"mcp_code_review.server",
"--parallelism",
"1",
"--concurrency-mode",
"auto",
"--timeout-seconds",
"2700",
"--profile",
"review"
]Tool behavior
Tool name:
review_uncommitted_changes.Uses the native app-server review target
uncommittedChanges(includes untracked files).Additional review instructions are enabled by default, exposing the
additional_developer_instructionstool argument.When that argument is set, the server switches that run to a custom review target prompt built from a synced copy of Codex's native uncommitted-changes instructions and appends an
Additional review instructions:section.Existing
--enable additional_review_instructionsusage is still accepted for backward compatibility.When disabled with
--disable additional_review_instructions, the tool schema does not advertiseadditional_developer_instructions, and requests that send it anyway are rejected.Default runs: 4 (override by setting
--parallelismon the MCP server config).Sandbox: read-only; approval policy: never.
Available Tools
1 toolreview_uncommitted_changesReview uncommitted changesB
Run Codex review on uncommitted changes using the app-server review API. Returns structured results for each run.
Inputs: cwd, runs, additional_developer_instructions. Returns: results
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity. The agent will always select the same tool for the server's purpose.
The single tool name follows a clear verb_noun pattern (review_uncommitted_changes), but consistency cannot be fully assessed with only one tool.
A single tool is very thin for a server. While it may serve a narrow purpose, it feels incomplete and limits the server's usefulness.
The tool only covers reviewing uncommitted changes. Obvious gaps include reviewing committed changes, specific files, or providing review history.
Maintenance
Related MCP Connectors
Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP.
CodeRide eliminates the context reset cycle once and for all. Through MCP integration, it seamless…
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Remote MCP for Copilot CLI switch gate MCP, structured receipts, audit logs, and reviewer-ready evid
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides MCP tools to review git changes using OpenAI Codex CLI, enabling code review of unstaged, staged, or last-commit changes.316 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables Grok Build to orchestrate the local Codex CLI for code reviews, adversarial reviews, task rescue, session transfer, and background job management through MCP tools.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA local, read-only Git change review tool that provides total workspace diffs, staged/unstaged views, file-level inspection, and task-scoped snapshots for MCP-compatible clients like Codex, Claude Code, and Cursor.MIT
- AlicenseNot gradedqualityCmaintenanceEnables Claude Code to delegate bounded, read-only analysis and isolated patch proposals to the locally installed Codex CLI over MCP, with sanitized live status, revision-aware polling, and reviewable results.1MIT