Gaffer runs on your own machine — the client starts it, so there is no endpoint to ping. 32 installs a week from npm. Last commit 11 Aug 2026.
Test analytics for AI agents: test history, flaky tests, failure clusters, coverage.
Today is the operative word: we check Gaffer every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp -- npx -y @gaffer-sh/mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@gaffer-sh/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@gaffer-sh/mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@gaffer-sh/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@gaffer-sh/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
GAFFER_API_KEY (API key from Account Settings > API Keys. gaf_ user key or gfr_ project token.), GAFFER_API_URL (Override the Gaffer API base URL. Defaults to https://app.gaffer.sh).
The author declared them in the registry entry; get the values from the project itself.
BuildPulse CI test analytics for AI agents — flaky tests, CI failures, flakiness, and code coverage.
Test generation, mocks, coverage analysis for AI agents
Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.
Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
MCP server for Blacksmith CI - query runs, analyze test failures, detect flaky tests.
Agent-first tech news: ranked story clusters, coverage and discussion links, trends, and events.
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
Analyze test coverage from LCOV files - makes AI agents coverage-aware without wasting tokens
Answers built from our own checks of this server.