# Sift

> Use this tool when you need to analyze and troubleshoot test failures from various test runners, such as pytest, Jest, or Maven, to identify root causes and detect patterns. It takes JUnit XML reports as input and outputs detailed failure analysis, pass/fail statistics, and severity trends, stored in a SQLite database. Ideal for use in continuous integration and testing pipelines to streamline error diagnosis and resolution.

Canonical page: https://skillsregistry.net/skills/sift-mcp-sift  
JSON: https://api.skillsregistry.net/v1/skills/sift-mcp-sift

## Description

Test intelligence server that parses JUnit XML reports from any test runner (pytest, Jest, Maven, Go test, Cargo) to extract root causes, detect cascade failures, and deduplicate errors via SHA-256 fingerprinting. Stores results in SQLite and exposes 6 tools for ingesting reports, analyzing results, querying failure history, detecting flaky tests, computing pass/fail statistics, and tracking severity trends. Built in Go with an npm wrapper for easy installation.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sift-mcp-sift)
- **Repository:** <https://github.com/sift-mcp/sift-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "sift-mcp-sift"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sift-mcp-sift` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sift-mcp-sift/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt