Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

PR Viewer Server

БесплатноНе проверен

Enables PR review workflows by launching a diff visualizer against a git repo and returning 'accepted' or 'rejected' based on user decision.

GitHubEmbed

Описание

Enables PR review workflows by launching a diff visualizer against a git repo and returning 'accepted' or 'rejected' based on user decision.

README

MCP server for local development workflows. Tools for branching and diff review, designed to be called by AI coding assistants.

Setup

uv sync --group dev

Tools

Tool Description
health_check Confirms the server is reachable.
open_branch Checks the working tree is clean, then creates a new branch.
open_review Launches a diff visualizer and blocks until the user accepts or rejects.

open_branch

Parameter Default Description
repo_path Absolute path to a git repo.
branch_name Name for the new branch.
base_ref main Ref to branch from.

Returns "Created branch '<name>' from <base_ref>" on success, or an error string describing why it failed (dirty tree, branch already exists, bad ref).

open_review

Parameter Default Description
repo_path Absolute path to a git repo.
base_ref main The base git ref (e.g. main, origin/main).
head_ref HEAD The head ref to diff against base (branch name, commit SHA, etc.).

Blocks until the user finishes reviewing. Returns "accepted" or "rejected".

Wiring in a visualizer

Create a shell script that receives the repo context via env vars, launches the visualizer, captures the user's decision, and signals the result back to the server via the provided IPC path:

#!/usr/bin/env bash
# Env vars provided by the server:
#   REPO_PATH   – absolute path to the git repo
#   BASE_REF    – base ref (e.g. main)
#   HEAD_REF    – head ref (e.g. feature/add-greet)
#   RESULT_PATH – IPC path the script writes "accepted" or "rejected" to

# launch your visualizer, capture the decision, then signal the result:
echo "accepted" > "$RESULT_PATH"

The default visualizer (scripts/launch-octorus.sh) opens octorus in a new terminal window and prompts accept/reject after the user quits.

Connecting to AI coding assistants

Claude Code

Add to ~/.claude/mcp.json (global) or .mcp.json at a project root:

{
  "mcpServers": {
    "devflow": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/pr-viewer", "devflow-mcp"]
    }
  }
}

OpenCode

opencode mcp add pr-viewer

Follow the prompts: choose stdio, set command to uv, args to run --directory /path/to/pr-viewer devflow-mcp. This writes to ~/.config/opencode/opencode.jsonc.

Codex

codex mcp add pr-viewer -- uv run --directory /path/to/pr-viewer devflow-mcp

This writes to ~/.codex/config.toml.

Example prompts

Create a branch called feature/add-login in /path/to/repo from main.
Open a review of feature/add-greet in /path/to/repo against main.
If it's accepted, merge it with `gh pr merge --merge`.
If it's rejected, post a comment explaining what needs to change.

Manual end-to-end test with a toy repo

1. Create the toy repo

./scripts/setup-toy-repo.sh

Creates ./toy-repo/ with a main branch and a feature/add-greet branch. To remove it when done:

./scripts/teardown-toy-repo.sh

2. Start the MCP inspector

uv run mcp dev src/devflow_mcp/server.py

Open the inspector URL printed in the terminal (default: http://localhost:5173).

3. Test open_branch

In the MCP inspector, select open_branch and fill in:

{
  "repo_path": "<absolute-path-to-project>/toy-repo",
  "branch_name": "test-branch"
}

4. Test open_review

Select open_review and fill in:

{
  "repo_path": "<absolute-path-to-project>/toy-repo",
  "base_ref": "main",
  "head_ref": "feature/add-greet"
}

The tool blocks — the inspector shows a spinner until the review is complete. A terminal window opens automatically; answer the accept/reject prompt when you quit octorus.

Programmatic use

import asyncio
from mcp.client.stdio import stdio_client, StdioServerParameters
from mcp.client.session import ClientSession

async def main() -> None:
    server = StdioServerParameters(
        command="uv",
        args=["run", "--directory", "/path/to/pr-viewer", "devflow-mcp"],
    )
    async with stdio_client(server) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            await session.call_tool("open_branch", {
                "repo_path": "/path/to/repo",
                "branch_name": "feature/my-feature",
            })
            result = await session.call_tool("open_review", {
                "repo_path": "/path/to/repo",
                "base_ref": "main",
                "head_ref": "feature/my-feature",
            })
            print(result.content[0].text)  # "accepted" or "rejected"

asyncio.run(main())

Tests

uv run pytest

from github.com/darenkeck-dev/devflow-mcp

Установка PR Viewer Server

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/darenkeck-dev/devflow-mcp

FAQ

PR Viewer Server MCP бесплатный?

Да, PR Viewer Server MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для PR Viewer Server?

Нет, PR Viewer Server работает без API-ключей и переменных окружения.

PR Viewer Server — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить PR Viewer Server в Claude Desktop, Claude Code или Cursor?

Открой PR Viewer Server на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare PR Viewer Server with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории development