MCP.Market

Gaffer MCP server

by gaffer.sh·sh.gaffer/mcp·v0.9.0·1 stars
No reviews yet

Test analytics for AI agents: test history, flaky tests, failure clusters, coverage.

B71/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B71/100

full report

Adoption
Growing

1 stars82 downloads/wk

Reviews

Write one

Nobody has reviewed Gaffer yet.

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

Gaffer tools (3, 2 write)

write = sends, deletes, buys or posts

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

  • execute_codewrite action
  • search_tools

    Search for available Gaffer API functions by keyword. Returns matching functions with their TypeScript declarations so you can use them with execute_code. Examples: - "coverage" → coverage-related functions - "flaky" → flaky test detection - "" (empty) → list all available functions

  • upload_test_resultswrite action

    Upload structured test results to Gaffer. Use this when you have test results in hand — parsed from CI output, a test runner's JSON report, or your own run — and no Gaffer CLI is available to upload them. Once uploaded, the results feed history, flaky detection, and health scores, so the read functions can see them on subsequent calls. Provide the tests; runId, the run timestamps and the pass/fail

Public scan report

scanner v0.1.10 · 2026-11-04 · same rubric, same numbers if you re-run it

1 medium
  • Code scan3 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 85 days ago12/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/index.js: … "require(", "import ", "import(", "eval(", "new Function", "Function(", "Buff…
Overall 71/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Gaffer compares

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

Safety score
71/100
higher than 36% of 48,255 servers
Tools
3
the typical server has 7
Tools that change things
67%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,688 servers
Downloads a week
82
more than 58% of 12,191 servers with a package

What its tools let an agent do: 1 read · 1 create · 1 run or deploy

Install Gaffer in Claude Code, Cursor or VS Code

Runs npx -y @gaffer-sh/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @gaffer-sh/mcp
Add to Cursor

What the publisher says

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

@gaffer-sh/mcp

MCP (Model Context Protocol) server for Gaffer - give your AI assistant memory of your tests.

What is this?

This MCP server connects AI coding assistants like Claude Code and Cursor to your Gaffer test history and coverage data. It runs in code mode: three MCP tools over a namespace of 17 functions — 16 read-only analytics functions plus uploadtestresults. It allows AI to:

  • Check your project's test health (pass rate, flaky tests, trends)
  • Look up the history of specific tests to understand stability
  • Get context about test failures when debugging
  • Analyze code coverage and identify untested areas
  • Browse all your projects (with user API Keys)
  • Access test report files (HTML reports, coverage, etc.)

Prerequisites

  1. A Gaffer account with test results uploaded
  2. An API Key from Account Settings > API Keys

Setup

Claude Code (CLI)

The easiest way to add the Gaffer MCP server is via the Claude Code CLI:

claude mcp add gaffer -e GAFFER_API_KEY=gaf_your_api_key_here -- npx -y @gaffer-sh/mcp

Claude Code (Manual)

Alternatively, add to your Claude Code settings (~/.claude.json or project .claude/settings.json):

{
  "mcpServers": {
    "gaffer": {
      "command": "npx",
      "args": ["-y", "@gaffer-sh/mcp"],
      "env": {
        "GAFFER_API_KEY": "gaf_your_api_key_here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "gaffer": {
      "command": "npx",
      "args": ["-y", "@gaffer-sh/mcp"],
      "env": {
        "GAFFER_API_KEY": "gaf_your_api_key_here"
      }
    }
  }
}

How this server works

This server uses code mode. Instead of exposing one MCP tool per API call, it exposes three tools plus a codemode namespace you call from JavaScript. Fewer tool definitions occupy the context window, and a single execution can chain several calls.

const health = await codemode.get_project_health({ projectId: "proj_abc" });
if (health.flakyTestCount > 0) {
  const flaky = await codemode.get_flaky_tests({ projectId: "proj_abc" });
  return { health, flaky };
}
return { health };

Functions available via execute_code

Shortened. The full README is on GitHub.

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

Gaffer: common questions

Is Gaffer MCP server safe?
Mostly: it is graded B (71/100). Read the Gaffer safety report
How do I install Gaffer?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Gaffer need an API key?
Yes. The registry entry asks for GAFFER_API_KEY.
Is Gaffer maintained?
The last commit was 85 days ago (2026-08-11). The latest release is v0.9.0.
How does Gaffer compare with other MCP servers?
safety score 71/100 (higher than 36% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 67% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.