Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.srbsa/diffgate

NPM · DIFFGATE-REVIEW · SCANNED SEP 20

Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens.

Available components

0 this week 94 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 11 of 30 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to srbsa/diffgate). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 54 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1004 tokens (~91/item across 11 items; 7 tools + 4 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.srbsa/diffgate MCP server?

io.github.srbsa/diffgate runs locally as an npm package, launched with npx -y diffgate-review. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · diffgate-review

# add to Claude Code
claude mcp add srbsa-diffgate -- npx -y diffgate-review
// .cursor/mcp.json
{
  "mcpServers": {
    "srbsa-diffgate": {
      "command": "npx",
      "args": [
        "-y",
        "diffgate-review"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "srbsa-diffgate": {
      "command": "npx",
      "args": [
        "-y",
        "diffgate-review"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add srbsa-diffgate -- npx -y diffgate-review
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "srbsa-diffgate": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "diffgate-review"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add srbsa-diffgate --command npx --arg -y --arg diffgate-review
# ~/.hermes/config.yaml
mcp_servers:
  srbsa-diffgate:
    command: "npx"
    args: ["-y", "diffgate-review"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "srbsa-diffgate": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "diffgate-review"
      ]
    }
  }
}
# add to Vellum
assistant mcp add srbsa-diffgate -t stdio -c npx -a -y diffgate-review
// mcp.json
{
  "mcpServers": {
    "srbsa-diffgate": {
      "command": "npx",
      "args": [
        "-y",
        "diffgate-review"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 18 Sept 26 +1
    • Stability: 0.97 → pass security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 11 Sept 26 +1
    • Stability: 0.97 → pass security
  • 9 Sept 26 +1
    • Schema quality: excellent → good functional
  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/diffgate-review@0.8.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo srbsa/diffgate
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/srbsa/diffgate/.github/workflows/publish-npm.yml@refs/tags/v0.8.0
Rekor log index 2258304621
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:514b59b750f9e5430cc2c50f25c0f1c588c009c0cfea32bebd8f1795d5bf3a94b5f2c2013cda5398cc7acd777ac9a561a031bee2876718c8fef9bfe88

Background: How many MCP packages publish verified provenance →

Dependencies 30 packages
Packages resolved 30
Stale 11
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~905 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
diffgate_analyze ~146

Analyze a file for code review findings. Only flags risk on lines changed vs the git baseline (diff-aware). Pass `content` to analyze unsaved or generated code before it is written to disk. When a code graph is available, public-surface findings carry an `impact` field (caller count, suggested reviewers, test gaps) and may be tier-adjusted — fix high-blast-radius findings before surfacing the code.

NameTypeReqDescription
contentstringFile content to analyze. Omit to read from disk.
cwdstringRepo root directory. Defaults to process.cwd().
filePathstringyesAbsolute or repo-relative path to the file.
NameTypeReqDescription
_diffgateobjectCapability hint: which layers (core/graph/llm) produced this result.
findingsarrayyesPer-line findings, each with ruleId, tier, line, and message.
tierstringyesOverall risk tier for the file.

No examples provided.

diffgate_capabilities ~84

Report which DiffGate layers are active (core / code graph / LLM), which tools you can call right now without an error, and the agent autonomy budget (fix limit, escalation, trust source). Call this once up front so you know what's available instead of discovering it via thrown errors.

NameTypeReqDescription
cwdstringRepo root. Defaults to process.cwd().
NameTypeReqDescription
agentobjectAutonomy budget: fix limit, escalation, trust source.
layersobjectWhich of core/graph/llm are active.
toolsarrayTool names callable without error right now.

No examples provided.

diffgate_check_staged ~132

Check all staged (or working-tree) changes in a git repo for DiffGate findings. Returns overall tier, counts, and per-file findings across the whole diff, plus a `verdict` block (the agent autonomy ladder: pass/review/blocked overall, with a rung — block/escalate/autofix/advisory — per finding) so you can decide whether to surface the diff without reimplementing the rules.

NameTypeReqDescription
cwdstringRepo root. Defaults to process.cwd().
modestringCheck staged-only or all working-tree changes. Default: working.
NameTypeReqDescription
_diffgateobjectCapability hint: which layers (core/graph/llm) produced this result.
filesarrayyesPer-file review results with findings.
tierstringyesOverall risk tier across the diff.
verdictobjectAgent autonomy ladder: pass/review/blocked, with a rung per finding.

No examples provided.

diffgate_deep_review ~133

Run an agentic deep review on a single high-impact (orange) finding. The model uses real repo tools (grep, read_file, find_references, git_blame) to investigate blast radius before rendering a verdict.

NameTypeReqDescription
cwdstringyesRepo root. Defaults to process.cwd().
filePathstringyesRepo-relative path of the file containing the finding.
findingobjectyesA finding object from diffgate_analyze.
languagestringLanguage id (javascript, python, go, etc.).
snippetstringCode snippet around the finding.
NameTypeReqDescription
rationalestringWhy the model reached that verdict.
toolStepsarrayThe investigation trace (tool calls the model made).
verdictstringyesThe model's final verdict on the finding.

No examples provided.

diffgate_explain ~92

Get a concise AI explanation for a DiffGate finding. Faster than diffgate_deep_review — a single LLM call with no tool loops.

NameTypeReqDescription
cwdstringyesRepo root. Defaults to process.cwd().
findingobjectyesA finding object from diffgate_analyze.
languagestringLanguage id.
snippetstringCode snippet around the finding.
NameTypeReqDescription
explanationstringyesA concise plain-language explanation of the finding.

No examples provided.

diffgate_feedback ~155

Record a reviewer's verdict on a finding so DiffGate learns. verdict 'dismiss' suppresses that same flagged code (ruleId + code) in future reviews (noise reduction); 'confirm' marks it as a real, valued catch. Stored in .diffgate/learnings.json at the repo root.

NameTypeReqDescription
codestringyesThe flagged code (finding.code).
cwdstringRepo root. Defaults to process.cwd().
filestringOptional repo-relative file path for context.
notestringOptional reviewer note (why).
ruleIdstringyesThe finding's ruleId.
verdictstringyesdismiss = noise/false-positive; confirm = real issue.
NameTypeReqDescription
recordedobjectyesThe stored learnings entry (ruleId, code, verdict, note, timestamp).

No examples provided.

diffgate_guidelines ~163

Review the diff against the repo's own coding guideline files (AGENTS.md, CLAUDE.md, .cursorrules, etc.), scoped per directory (nearest file wins). IMPORTANT: if the result has mode='host', NO external model was used — this is a SELF-REVIEW, not an independent gate: YOU (the calling agent) evaluate each group's `hunks` against its `guidelines` text using your own model. Treat host-mode results as ADVISORY only — never block the change on them. If mode='model', findings were produced by the configured provider and are returned directly.

NameTypeReqDescription
cwdstringRepo root. Defaults to process.cwd().
modestringDiff scope. Default: working.
NameTypeReqDescription
groupsarrayPer-guideline-file groups of hunks (host mode) or findings (model mode).
modestringyes'host' = self-review (advisory only); 'model' = an external provider produced findings.

No examples provided.

Common questions

What is the io.github.srbsa/diffgate MCP server?

io.github.srbsa/diffgate is an MCP server listed in the public MCP registry as io.github.srbsa/diffgate. Deterministic guardrail your coding agent runs on itself: diff-scoped findings, zero LLM tokens. This page covers its npm package (diffgate-review).

Is the io.github.srbsa/diffgate MCP server safe to use?

io.github.srbsa/diffgate scores 94 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.srbsa/diffgate MCP server expose?

io.github.srbsa/diffgate exposes 7 tools: diffgate_analyze, diffgate_check_staged, diffgate_deep_review, diffgate_explain, diffgate_capabilities, and 2 more. Their descriptions and schemas cost roughly 905 tokens of context every time the server is loaded.

Is the io.github.srbsa/diffgate MCP server still maintained?

io.github.srbsa/diffgate is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.srbsa/diffgate MCP server under?

io.github.srbsa/diffgate declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.