@maxronner/tea-mcp

@maxronner/tea-mcp

Enables AI assistants to manage Gitea repositories, issues, and pull requests via the tea CLI, including full PR review workflows.

Category
Visit Server

README

@maxronner/tea-mcp

CI npm version License: MIT

MCP (Model Context Protocol) server for tea CLI - interact with Gitea repositories, issues, and pull requests from AI assistants.

Features

  • List, view, create, close, and reopen issues
  • List, view, and checkout pull requests
  • Create pull requests with preview mode - review changes before creating
  • Approve and reject pull requests - complete PR review workflow
  • Merge pull requests - with multiple merge strategies (merge, squash, rebase)
  • List and view repository details
  • Full integration with MCP-compatible AI tools

Prerequisites

  • Node.js 18+
  • tea CLI installed and configured with your Gitea instance

Installation

Option 1: NPX (Recommended)

npx @maxronner/tea-mcp

Option 2: Global Install

# Using npm
npm install -g @maxronner/tea-mcp

# Using bun
bun install -g @maxronner/tea-mcp

Option 3: Use with MCP Client

Add to your MCP client configuration (e.g., Claude Desktop, Cline):

{
  "mcpServers": {
    "tea": {
      "command": "npx",
      "args": ["@maxronner/tea-mcp"]
    }
  }
}

Available Tools

Issue Tools

tea_issues_list

List issues in the current repository.

Parameters:

  • state (optional): "open" | "closed" | "all" (default: "open")
  • limit (optional): 1-100 (default: 30)
  • labels (optional): Filter by labels (comma-separated)
  • author (optional): Filter by author

tea_issue_view

View details of a specific issue.

Parameters:

  • index (required): Issue number

tea_issue_close

Close an issue.

Parameters:

  • index (required): Issue number

tea_issue_reopen

Reopen a closed issue.

Parameters:

  • index (required): Issue number

Pull Request Tools

tea_prs_list

List pull requests in the current repository.

Parameters:

  • state (optional): "open" | "closed" | "all" (default: "open")
  • limit (optional): 1-100 (default: 30)

tea_pr_view

View details of a specific pull request.

Parameters:

  • index (required): Pull request number

tea_pr_checkout

Checkout a pull request locally.

Parameters:

  • index (required): Pull request number to checkout

tea_pr_create

Create a new pull request with optional preview mode.

Parameters:

  • title (required): Pull request title
  • description (optional): PR body/description
  • head (optional): Source branch name (defaults to current branch)
  • base (optional): Target branch name (defaults to the repository default branch)
  • preview (optional): Show diff without creating PR (default: false)
  • assignees (optional): Comma-separated usernames to assign
  • labels (optional): Comma-separated labels to assign
  • milestone (optional): Milestone to assign

Usage:

// Preview what the PR will include
{ "title": "My Feature", "preview": true }

// Create the actual PR
{ "title": "My Feature", "description": "Adds cool feature", "base": "main" }

tea_pr_approve

Approve a pull request.

Parameters:

  • index (required): Pull request number to approve
  • comment (optional): Approval comment

Example:

{ "index": 42, "comment": "LGTM! Great work." }

tea_pr_reject

Request changes on a pull request.

Parameters:

  • index (required): Pull request number to reject
  • reason (required): Reason for requesting changes

Example:

{ "index": 42, "reason": "Please fix the variable naming convention" }

tea_pr_merge

Merge a pull request.

Parameters:

  • index (required): Pull request number to merge
  • style (optional): Merge strategy - "merge" | "rebase" | "squash" | "rebase-merge" (default: "merge")
  • title (optional): Custom merge commit title
  • message (optional): Custom merge commit message

Example:

// Standard merge
{ "index": 42 }

// Squash merge with custom message
{ "index": 42, "style": "squash", "message": "Squashed feature commits" }

Repository Tools

tea_repos_list

List repositories you have access to.

Parameters:

  • limit (optional): 1-100 (default: 30)
  • type (optional): "fork" | "mirror" | "source"

tea_repo_view

View details of a repository.

Parameters:

  • repo (optional): Repository in "owner/name" format (defaults to current repo)

Development

Setup

git clone https://github.com/maxronner/tea-mcp.git
cd tea-mcp
bun install

Commands

bun run build         # Build TypeScript
bun test              # Run tests
bun run test:run      # Run tests once
bun run test:coverage # Run tests with coverage
bun run lint          # Run ESLint
bun run lint:fix      # Fix lint issues
bun run format        # Format with Prettier
bun run typecheck     # Type check without emit

Testing

This project uses bun:test with mocked child process execution to test without requiring the tea CLI.

Coverage threshold: 80%

Important Notes

Self-Approval in Gitea

Gitea allows PR authors to approve their own pull requests by default. This is different from GitHub's default behavior. Here's what you need to know:

  • Default behavior: PR authors can approve their own PRs, and these approvals count toward any required approval count
  • Branch protection: To enforce proper review workflows, use branch protection rules:
    • Set "Required approving reviews" to a higher number (e.g., 2+) to ensure external review
    • Enable "Require review from Code Owners" and define a CODEOWNERS file
    • Consider enabling BlockAdminMergeOverride to prevent even admins from bypassing rules

Recommended Branch Protection Setup

  1. Navigate to Repository Settings → Branches → Branch Protection Rules
  2. Enable "Require pull request reviews before merging"
  3. Set "Required approving reviews" to at least 2
  4. Create a .gitea/CODEOWNERS file:
# Default reviewers for all changes
* @team-lead @senior-devs

# Specific paths require specific reviewers
/src/**/*.ts @typescript-maintainers
/docs/** @documentation-team
  1. Enable "Require review from Code Owners" in branch protection

This ensures proper code review even when working solo or in small teams.

Contributing

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/my-feature
  3. Make your changes and ensure tests pass: bun run test:run
  4. Commit with conventional commits
  5. Push and create a pull request

License

MIT (c) Max Ronner

Links

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured