MCP.so
Sign In
S

Swipr

@nochinxx

About Swipr

Swipe-to-review GitHub PRs with AI context. Paste a repo URL, get open PRs as a card stack with risk scores, AI summaries, similar past changes, and contributor history. Works as a Claude MCP plugin — review PRs directly from Claude Desktop or Cursor without a browser. 12 tools i

Basic information

Category

Version Control

Transports

stdio

Publisher

nochinxx

Submitted by

Mario Jimenez

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "swipr": {
      "command": "npx",
      "args": [
        "-y",
        "supergateway",
        "--streamableHttp",
        "https://v0-swipr-build.vercel.app/api/mcp"
      ]
    }
  }
}

Tools

12

Resolve `owner/repo#number` → internal ID

Full PR data: files, patches, risk score, contributor stats, cached AI summary

0–100 heuristic score with reasons

Past PRs in the same repo with semantic similarity

PR count, merge rate, first contribution date

Raw file content at HEAD

Search patches for usages of a function name

Test files that likely cover the changed code

Recent contributors to a file path

File content at an arbitrary git ref

Capture approve / changes / skip

End-of-session stats

Overview

What is Swipr?

Swipr is a swipe-to-review interface for GitHub pull requests, providing AI-generated context such as risk scores, contributor history, similar past changes, and test coverage. It works as both a web app and an MCP (Model Context Protocol) server, enabling human reviewers and AI agents (e.g., Claude) to triage PRs quickly.

How to use Swipr?

Add the MCP server to Claude Desktop by editing claude_desktop_config.json with the provided npx command using Supergateway and the hosted endpoint. Once configured, ask Claude to analyze PRs via tools like lookup_pr, analyze_pr, or find_similar_changes. The web app at the demo URL lets you paste a public repo, then swipe right (approve), left (request changes), or down (skip) with keyboard shortcuts (J, F, Space).

Key features of Swipr

  • Swipe-based UI for rapid PR triaging
  • MCP server with 12 read-only tools (e.g., analyze_pr, risk_score, find_related_tests)
  • Heuristic risk scoring (0–100, configurable in lib/scoring.ts)
  • Cached AI summaries per PR — no repeated API calls
  • Bring-your-own-AI-key chat (supports Groq, Google Gemini, Anthropic)
  • Self-hostable on Neon Postgres + pgvector + Vercel AI Gateway
  • All MCP tools are pure database reads — zero AI credits consumed

Use cases of Swipr

  • Maintainers quickly triaging a large backlog of open PRs
  • AI agents (e.g., Claude) deciding whether to merge a PR based on risk and context
  • Finding tests that cover a changed file before approving
  • Comparing a PR with semantically similar past changes to spot regressions
  • Onboarding new contributors by surfacing their history and merge rate

FAQ from Swipr

What is the difference between the web app and the MCP server?

Both surface the same PR context (risk, similar changes, contributor history, tests). The web app provides a visual swipe interface for humans; the MCP server lets AI agents like Claude access the same data programmatically.

What are the data storage and limits?

Self-hosted Swipr stores PR data in Neon Postgres with pgvector. The free-tier Neon instance (512 MB) holds roughly 5,000 PRs (~100 KB each). Ingestion is capped at 100 open PRs per repo.

How can I customize the risk scoring?

The risk heuristic is defined in lib/scoring.ts as plain TypeScript (no ML). You can add or adjust rules, e.g., increase score when auth files are touched. Color thresholds (green/yellow/red) at 40 and 70 are set in app/swipe/_components/view-helpers.ts.

Does the MCP server require authentication or consume AI credits?

The hosted MCP server uses no authentication — the URL is public. All 12 tools are pure database reads; no AI API calls are made, so no AI credits are consumed. The chat

Comments

More Version Control MCP servers