MCP.Market

Evidence Diff MCP server

by mrfentmen·io.github.mrfentmen/evidence-diff-mcp·v1.0.1

Explain coarse Git and test-build evidence changes without source diff contents. Tools include...

A85/100grade A
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
New

0 stars126 downloads/wk

Reviews

Write one

Nobody has reviewed Evidence Diff yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Evidence Diff tools (1)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • explain_change_evidence

    Explain coarse changes in local Git and test-build evidence without returning source diffs, file contents, or secrets.

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

no findings
  • Code scan8 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 84 days ago12/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Evidence Diff compares

Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 70% of 1,119 Developer tools servers
Tools
1
the typical Developer tools server has 7
Tools that change things
0%
typical: 5%. Fewer write tools means less an agent can break
Downloads a week
126
more than 63% of 436 Developer tools servers with a package

What its tools let an agent do: 1 read

Release history: 2 versions in the registry since 2026-09-21, latest 2026-09-21, typically several a day.

Install Evidence Diff in Claude Code, Cursor or VS Code

Runs npx -y evidence-diff-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add evidence-diff-mcp -- npx -y evidence-diff-mcp
Add to Cursor

What the publisher says

From the Evidence Diff repository's README, as published. We do not edit it. Read it on GitHub

evidence-diff-mcp

Evidence Diff is a local MCP tool for explaining coarse changes in a Git project’s test and build evidence. It can tell an agent that a worktree changed, that uncommitted evidence exists, or that test-like artifacts appear without build-like artifacts, without exposing source diffs.

Tool

  • explainchangeevidence: inspect local Git state and bounded top-level evidence names.

Safety

  • Local paths only, bounded by EVIDENCEDIFFROOT and realpath checks.
  • Returns only counts, coarse categories, coarse branch state, and commit dates.
  • Never returns source diffs, evidence filenames, branch names, file paths from Git output, commit subjects, authors, command output, file contents, or secrets.
  • Does not execute tests, builds, or arbitrary project commands.
  • This is an evidence explanation aid, not a code review or CI oracle.

Run

npm install
npm run build
node dist/index.js

Nothing above is checked by us. What we check is on the safety report.

Evidence Diff: common questions

Is Evidence Diff MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Evidence Diff safety report
How do I install Evidence Diff?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Evidence Diff need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Evidence Diff maintained?
The last commit was 87 days ago (2026-08-09). The latest release is v1.0.1.
What can I use instead of Evidence Diff?
Servers from other publishers that do the same job: RepoPilot MCP server, Ekbasis MCP server and diffctx MCP server.
How does Evidence Diff compare with other Developer tools MCP servers?
safety score 85/100 (higher than 70% of 1,119 Developer tools servers); tools 1 (the typical Developer tools server has 7); tools that change things 0% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Evidence Diff

Same job from other publishers: the closest match first, then the best rated.

  • RepoPilot
    Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.
    A
  • Ekbasis
    Foresee what git commands and multi-step changes will do, as calibrated probabilities
    B
  • diffctx
    Selects the minimum code an LLM needs to review a git diff
    A
  • Mason
    Engineering decisions, change impact, documentation audits, and CI evidence for coding assistants.
    A
  • Nexusmem
    Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.
    A

More from mrfentmen →