How should pr-review-mcp be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this mcp.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

pr-review-mcp answer-first brief

MCP server for PR review processing with GraphQL-based GitHub integration pr-review-mcp 🤖 **The ultimate Model Context Protocol (MCP) server for orchestrating AI-driven Pull Request reviews.** pr-review-mcp bridges the gap between GitHub's complex GraphQL API and AI agents. It standardizes PR review data from tools like CodeRabbit, Gemini, Copilot, and Sourcery, enabling intelligent agents to read, resolve, and manage code reviews programmatically. --- 🚀 Why This Exists Reviewing code is Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Freshness

Last checked 2/22/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

pr-review-mcp is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 100/100

pr-review-mcp

MCPverified

Public facts

Change events

Artifacts

Freshness

Feb 22, 2026

Verifiededitorial-content1 verified compatibility signal

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Schema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

MCP

Freshness

Feb 22, 2026

Vendor

Thebtf

Artifacts

Benchmarks

Last release

0.1.4

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

View Source

Setup snapshot

git clone https://github.com/thebtf/pr-review-mcp.git

1
Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Thebtf

profilemedium

Observed Feb 24, 2026Source link Provenance

Compatibility (2)

Protocol compatibility

MCP

contracthigh

Observed Feb 24, 2026Source link Provenance

Auth modes

mcp, api_key

contracthigh

Observed Feb 24, 2026Source link Provenance

Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh

Observed Feb 24, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB MCP

Extracted files

Examples

Snippets

Languages

typescript

Executable Examples

mermaid

graph TD
    User[Client / Agent] -->|MCP Protocol| Server[pr-review-mcp]
    
    subgraph "Core Logic"
        Server --> Tools[Tool Handlers]
        Server --> Extractors[Prompt/Nitpick Extractors]
        Server --> Coordination[State & Coordination]
    end
    
    subgraph "External"
        Tools -->|GraphQL / REST| GitHub[GitHub API]
        Coordination -->|Shared State| Workers[Parallel Agents]
    end
    
    Extractors -.->|Parse| GitHub

bash

npm install -g pr-review-mcp

bash

npm install -g pr-review-mcp@latest

json

{
  "mcpServers": {
    "pr": {
      "command": "pr-review-mcp",
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

bash

git clone https://github.com/thebtf/pr-review-mcp.git
cd pr-review-mcp
npm install && npm run build

json

{
  "mcpServers": {
    "pr": {
      "command": "node",
      "args": ["/path/to/pr-review-mcp/dist/index.js"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB MCP

Docs source

GITHUB MCP

Editorial quality

ready

Full README

pr-review-mcp 🤖

The ultimate Model Context Protocol (MCP) server for orchestrating AI-driven Pull Request reviews.

pr-review-mcp bridges the gap between GitHub's complex GraphQL API and AI agents. It standardizes PR review data from tools like CodeRabbit, Gemini, Copilot, and Sourcery, enabling intelligent agents to read, resolve, and manage code reviews programmatically.

🚀 Why This Exists

Reviewing code is hard; managing AI reviews is harder. Modern CI/CD pipelines often include multiple AI reviewers (CodeRabbit for summaries, Qodo for testing, Gemini for logic), creating a noisy flood of comments.

This server solves the "AI-on-AI" coordination problem:

Unified Interface: One standard API to fetch comments from any supported AI agent.
Noise Reduction: Automatically splits multi-issue comments and extracts "nitpicks" from bodies.
Resolution Logic: Allows agents to resolve outdated threads via GraphQL mutations.
Parallelism: Coordinates multiple worker agents to process reviews simultaneously without collision.

✨ Key Features

🔌 GraphQL-Powered Integration: Efficient cursor-based pagination for large PRs.
🤖 Multi-Agent Orchestration: Native support for CodeRabbit, Gemini, Copilot, Sourcery, Qodo, and Codex.
🧠 Prompt Extraction: Automatically parses the underlying prompt used by AI agents from comment metadata.
⚡ Parallel Coordination: Built-in specialized tools (claim_work, report_progress) for multi-worker setups, with hybrid Task UI monitoring for real-time progress visibility.
🔒 Branch Protection: Refuses to process a different PR when on a feature branch with an open PR, preventing merge conflicts in worktree setups.
🛡️ Resilience: Implements Circuit Breaker patterns and robust retry logic for GitHub API stability.
🧹 Smart Parsing:
- Nitpick Extraction: Isolates minor issues from CodeRabbit summaries.
- Multi-issue Splitting: Breaks down monolithic comments into actionable items.
- Qodo Tracking: Persistently tracks Qodo comments across commits.

🏗️ Architecture

graph TD
    User[Client / Agent] -->|MCP Protocol| Server[pr-review-mcp]
    
    subgraph "Core Logic"
        Server --> Tools[Tool Handlers]
        Server --> Extractors[Prompt/Nitpick Extractors]
        Server --> Coordination[State & Coordination]
    end
    
    subgraph "External"
        Tools -->|GraphQL / REST| GitHub[GitHub API]
        Coordination -->|Shared State| Workers[Parallel Agents]
    end
    
    Extractors -.->|Parse| GitHub

🛠️ Tools

The server exposes 16 optimized tools for agents.

📊 Analysis & Retrieval

| Tool | Description | |------|-------------| | pr_summary | Get high-level stats (open threads, severity counts). | | pr_list | List comments with advanced filtering (resolved status, file path). | | pr_list_prs | List open pull requests with activity stats. | | pr_get | Get deep details for a specific comment, including the AI prompt. | | pr_changes | Poll for incremental updates since a specific cursor. | | pr_poll_updates | Poll for new comments and agent completion status. |

⚡ Action & Management

| Tool | Description | |------|-------------| | pr_resolve | Mark a review thread as resolved. | | pr_invoke | Trigger a specific AI agent (e.g., CodeRabbit) to re-review. | | pr_labels | Add, remove, or list PR labels. | | pr_reviewers | Request or remove human/team reviewers. | | pr_create | Create a new PR from branches. | | pr_merge | Merge a PR (squash/merge/rebase) with safety checks. |

🧩 Orchestration (Multi-Agent)

| Tool | Description | |------|-------------| | pr_claim_work | Lock a partition of files for a worker agent. | | pr_report_progress | Report status (done/failed) for a claimed task. | | pr_get_work_status | View global orchestration status. | | pr_reset_coordination | Reset coordination state (destructive, requires confirmation). |

📝 MCP Prompts

The server provides two MCP prompts for guided workflows:

| Prompt | Description | |--------|-------------| | review (/pr:review) | Autonomous multi-agent PR review orchestrator. Spawns parallel workers to process all AI review comments, with real-time Task UI monitoring. | | setup (/pr:setup) | Guided onboarding for .github/pr-review.json configuration — agent selection, env config, priority. |

💻 Quick Start

Prerequisites

Node.js 18+
A GitHub Personal Access Token (PAT) with repo scope

Installation

npm install -g pr-review-mcp

To update to the latest version:

npm install -g pr-review-mcp@latest

MCP Client Setup

Add to ~/.claude/settings.json (Claude Code) or claude_desktop_config.json (Claude Desktop):

{
  "mcpServers": {
    "pr": {
      "command": "pr-review-mcp",
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

The token is passed via the MCP config — no need to set environment variables globally.

<details> <summary>Alternative: from local clone</summary>

git clone https://github.com/thebtf/pr-review-mcp.git
cd pr-review-mcp
npm install && npm run build

{
  "mcpServers": {
    "pr": {
      "command": "node",
      "args": ["/path/to/pr-review-mcp/dist/index.js"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

To update: git pull && npm install && npm run build

</details>

🔍 Examples

Get PR Summary

{
  "owner": "owner-name",
  "repo": "repo-name",
  "pr": 123
}

Result:

{
  "total": 45,
  "unresolved": 3,
  "bySeverity": {
    "CRIT": 1,
    "MAJOR": 2,
    "MINOR": 40
  }
}

Invoke AI Reviewer

{
  "owner": "owner-name",
  "repo": "repo-name",
  "pr": 123,
  "agent": "coderabbit"
}

Multi-Agent Orchestration

{
  "agent_id": "worker-1",
  "pr_info": { "owner": "org", "repo": "repo", "pr": 42 }
}

🔗 Related Projects

Serena MCP — Code navigation and symbol-level editing for workers
MCP Specification — Model Context Protocol standard

📜 License

MIT © thebtf

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

Verifiedcapability-contract

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

ready

Auth

mcp, api_key

Streaming

Data region

global

Protocol support

MCP: verified

Requires: mcp, lang:typescript

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.

Trust confidence is not low and verification freshness is acceptable.

Protocol support is explicitly confirmed in contract metadata.

Invocation examples

curl -s "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/snapshot"

curl -s "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract"

curl -s "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

Ard RegistryUpdated 0h agoRank 94

ShortlistLens

Structured website and review evidence for AI-assisted local-business shortlisting.

MCPmcpmcp-registry

Ard RegistryUpdated 0h agoRank 94

Inferventis MCP Server

Loan & mortgage calculator, compound interest, ROI, crypto prices, FX conversion for AI agents.

MCPmcpmcp-registry

Ard RegistryUpdated 0h agoRank 94

io.github.cyanheads/reliefweb-mcp-server

Search ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP.

MCPmcpmcp-registry

Ard RegistryUpdated 0h agoRank 94

io.github.Deesmo/arch-tools-mcp

63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.

MCPmcpmcp-registry

Machine Appendix

Contract JSON

{
  "contractStatus": "ready",
  "authModes": [
    "mcp",
    "api_key"
  ],
  "requires": [
    "mcp",
    "lang:typescript"
  ],
  "forbidden": [],
  "supportsMcp": true,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": "https://github.com/thebtf/pr-review-mcp#input",
  "outputSchemaRef": "https://github.com/thebtf/pr-review-mcp#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:45:31.038Z",
  "sourceUpdatedAt": "2026-02-24T19:45:31.038Z",
  "freshnessSeconds": 19555141
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "MCP"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_MCP",
      "generatedAt": "2026-10-09T03:44:32.559Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "MCP",
      "type": "protocol",
      "support": "supported",
      "confidenceSource": "contract",
      "notes": "Confirmed by capability contract"
    },
    {
      "key": "mcp",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "coderabbit",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "github",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "pr-review",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "code-review",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "model-context-protocol",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "graphql",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "cli",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:MCP|supported|contract capability:mcp|supported|profile capability:coderabbit|supported|profile capability:github|supported|profile capability:pr-review|supported|profile capability:code-review|supported|profile capability:model-context-protocol|supported|profile capability:graphql|supported|profile capability:cli|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "MCP",
    "href": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:45:31.038Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "mcp, api_key",
    "href": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:45:31.038Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/thebtf/pr-review-mcp#input",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:45:31.038Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Thebtf",
    "href": "https://github.com/thebtf/pr-review-mcp",
    "sourceUrl": "https://github.com/thebtf/pr-review-mcp",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-thebtf-pr-review-mcp/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]