Gerrit Code ReviewSAFE
This MCP server provides integration with Gerrit code review system, allowing AI assistants to review code changes and their details through a simple interface.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@cayirtepeomer/gerrit-code-review-mcp)
This MCP server provides integration with Gerrit code review system, allowing AI assistants to review code changes and their details through a simple interface.
Features
The server provides a streamlined toolset for code review:
Fetch Change Details
fetch_gerrit_change(change_id: str, patchset_number: Optional[str] = None)
- Fetches complete change information including files and patch sets
- Shows detailed diff information for each modified file
- Displays file changes, insertions, and deletions
- Supports reviewing specific patch sets
- Returns comprehensive change details including:
- Project and branch information
- Author and reviewer details
- Comments and review history
- File modifications with diff content
- Current patch set information
Compare Patchset Differences
fetch_patchset_diff(change_id: str, base_patchset: str, target_patchset: str, file_path: Optional[str] = None)
- Compare differences between two patchsets of a change
- View specific file differences or all changed files
- Analyze code modifications across patchset versions
- Track evolution of changes through review iterations
Submit Review Feedback
submit_gerrit_review( change_id: str, message: Optional[str] = None, patchset_number: Optional[str] = None, labels: Optional[Dict[str, int]] = None, comments: Optional[List[Dict[str, Any]]] = None, notify: str = "OWNER", )
- Post summary feedback, vote labels (e.g.,
{"Code-Review": 1}), and inline/file-level comments - Target a specific patchset or default to the latest revision
- Control Gerrit's notification behaviour (
notify:NONE,OWNER,OWNER_REVIEWERS,ALL) - Comment payloads accept dictionaries with
path,message, and optional Gerrit comment fields (line
d2887daecd6fOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add gerrit-review-mcp --env GERRIT_AUTH_METHOD=${GERRIT_AUTH_METHOD} --env GERRIT_HTTP_PASSWORD=${GERRIT_HTTP_PASSWORD} --env GERRIT_PASSWORD=${GERRIT_PASSWORD} -- uvx gerrit-review-mcp{
"mcpServers": {
"gerrit-review-mcp": {
"command": "uvx",
"args": [
"gerrit-review-mcp"
],
"env": {
"GERRIT_AUTH_METHOD": "${GERRIT_AUTH_METHOD}",
"GERRIT_HTTP_PASSWORD": "${GERRIT_HTTP_PASSWORD}",
"GERRIT_PASSWORD": "${GERRIT_PASSWORD}"
}
}
}
}Exposed tools (3)
2 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
fetch_gerrit_change | read | |
fetch_patchset_diff | read | |
submit_gerrit_review | write | Submit a review message (and optional votes/comments) to Gerrit. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.env.template
.env.test
mcp, python-dotenv, requests, pytest, pytest-cov, black, isort, mypy
- Gerrit HTTP access credentials
Gates applied: no_behavioural_pass, no_license.
d2887daecd6ffull audit observations/trust-audit/mcp-server/cayirtepeomer__gerrit-code-review.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | d2887daecd6f | SAFE | B | 89 | first audit |
Questions
What is the Gerrit Code Review MCP server?
This MCP server provides integration with Gerrit code review system, allowing AI assistants to review code changes and their details through a simple interface.
What tools does Gerrit Code Review expose?
3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Gerrit Code Review safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Gerrit Code Review need?
It reads GERRIT_AUTH_METHOD, GERRIT_HTTP_PASSWORD and GERRIT_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Gerrit Code Review run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as gerrit-review-mcp.
How current is this page?
The grade is for one exact copy of the source (d2887daecd6f), read on 2026-10-08. The repository is watched and re-audited when it changes.