Skip to main content
Glama
pluto-atom-4

mcp-gh-forge

by pluto-atom-4
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

mcp-gh-forge 🛠️

mcp-gh-forge is a lightweight, ultra-minimal Model Context Protocol (MCP) server designed to act as a secure proxy between your AI terminal assistants (Claude Code and GitHub Copilot CLI) and your local automation workflows.

Instead of forcing your AI model to execute slow, separate, step-by-step commands, mcp-gh-forge lets the AI run robust, multi-step local Git operations and cloud GitHub API macros simultaneously through a single execution layer.

💎 Features

  • Dual-Universe Automation: Bridges local workspace operations (Git branches, files, builds) and remote cloud platform operations (GitHub Issues, Pull Requests).

  • Token & Cost Efficiency: Packs multi-stage developer chores into single-turn executions, slashing LLM context window bloat and API latency.

  • Cross-Platform Compatibility: Runs identically on Debian 13 and Windows 11 (Git Bash).

  • Fail-Safe Security Boundary: The AI cannot execute arbitrary terminal commands. It is bounded strictly to the execution parameter switches defined in your script blueprint directory.

Related MCP server: Git MCP Server

📂 Project Structure

mcp-gh-forge/
├── index.js             # Core MCP Node.js server bridge
├── package.json         # Node.js module configuration
└── README.md            # Documentation

🚀 Getting Started

1. Prerequisites

Ensure you have Node.js (v18+) installed on your local operating system.

2. Installation

Clone or navigate into your server folder and set up your project dependencies:

# Initialize project directory
cd mcp-gh-forge
npm install

3. Exposing Your Custom Automations

By default, the server expects your automated shell script (git-orchestrator.sh) to reside in your local machine's user path (~/bin/mcp-git-helpers/).

Make sure your shell scripts are executable (especially on Linux/Debian):

chmod +x ~/bin/mcp-git-helpers/git-orchestrator.sh

🔌 Linking to Your AI Assistants

To connect mcp-gh-forge to Claude Code, update your global ~/.claude.json configuration profile.

For Debian 13

{
  "mcpServers": {
    "mcp-gh-forge": {
      "command": "node",
      "args": ["/home/yourusername/projects/mcp-gh-forge/index.js"],
      "env": {
        "MCP_SCRIPT_DIR": "/home/yourusername/bin/mcp-git-helpers"
      }
    }
  }
}

For Windows 11 (Git Bash)

Note: Always use forward slashes (/) for paths within your JSON string parameters to ensure seamless cross-platform execution runtime support.

{
  "mcpServers": {
    "mcp-gh-forge": {
      "command": "node",
      "args": ["C:/Users/YourName/projects/mcp-gh-forge/index.js"],
      "env": {
        "MCP_SCRIPT_DIR": "C:/Users/YourName/bin/mcp-git-helpers"
      }
    }
  }
}

🛠️ Expose Actions & Capabilities

Once connected, mcp-gh-forge exposes the run_forge_macro tool to your interactive terminal sessions. The tool accepts the following parameters:

Action

Core Responsibility

Expected Argument Parameter

consolidate

Pulls issue/PR logs & comments together.

PR or Issue Number (45)

get-changed-files

Extracts unique lists of updated files.

Revision Tag or Git Hash (v2.1.0)

draft-and-save

Creates a local MD file & drafts a live GH issue.

Issue Title ("Bug: Auth Loop Failure")

branch-init

Safely fetches main & initializes clean branch.

New Branch Suffix ("login-fix")

branch-cleanup

Hard purges and cleans a dead branch layout.

Targeted Branch Suffix ("login-fix")

🦾 Usage Example

Launch your interactive assistant inside any active target git repository:

claude

Use natural language commands to kick off your automated multi-step processes:

"Use mcp-gh-forge to run get-changed-files for v1.0.4. Analyze the output and write an engine summary changelog."

"Please initialize a new local feature branch using action branch-init for argument user-dashboard-patch."

Available Tools

1 tool
run_forge_macroB

Executes powerful multi-step local Git and cloud GitHub automated scripts (consolidate, get-changed-files, draft-and-save, branch-init, branch-cleanup).

ParametersJSON Schema
NameRequiredDescriptionDefault
actionYesThe targeted script action block to execute.
argumentYesThe parameter required by the action (e.g., Issue title, PR number, commit revision hash).

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It describes the tool as 'powerful multi-step' but does not disclose potential side effects (e.g., destructive operations like 'branch-cleanup'), required permissions, or behavioral details beyond the action names. This is insufficient for a script execution tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the tool's purpose and lists all actions. It is front-loaded with the verb and resource. Slightly longer descriptions could add more details without being verbose, but it is concise enough.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema is present, and the description does not mention return values, error behaviors, or post-execution state. For a multi-step automation tool, this leaves significant gaps for the agent. The description is incomplete for safe and correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters having descriptions in the schema. The tool description adds the list of enum values but does not explain each action's purpose or the argument format beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verb 'executes' and identifies the resource as 'multi-step local Git and cloud GitHub automated scripts'. It lists all five script actions, making the tool's function clear and distinguishing it from potential siblings (though none exist).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lists the available actions but provides no guidance on when to use each action or when to choose this tool over alternatives. No explicit usage context, when-not, or alternative tools are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • First observedrun_forge_macro
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.3/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools. The single tool is clearly named and described.

Naming Consistency5/5

With only one tool, naming consistency is trivially maintained. The tool follows a verb_noun pattern.

Tool Count1/5

A single tool is extremely thin for a server named 'mcp-gh-forge', which implies a broader scope. Packing multiple operations into one macro tool is poor design.

Completeness2/5

The tool bundles several scripts (consolidate, get-changed-files, etc.) but lacks granular tools for individual operations, making the surface incomplete for typical GitHub automation workflows.

Maintenance

ActivitySlowing
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • GitPilot MCP

    DarkRyan721
    A
    license
    Not graded
    quality
    Not graded
    maintenance
    A lightweight MCP server that enables AI assistants to manage local Git repositories by executing commands like status, add, and commit. It streamlines development workflows by providing repository context and diffs directly to the assistant.
    -

  • Git MCP Server

    wty0512
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that provides tools for interacting with Git repositories, enabling AI assistants to manage repositories, branches, commits, and files through a standardized interface.
    7,389
    1
    Apache 2.0

  • local-git-mcp

    jrokeach
    A
    license
    Not graded
    quality
    D
    maintenance
    A lightweight MCP server that handles git operations on behalf of AI coding assistants, running as a local HTTP service without external network exposure by default.
    MIT

  • my-local-mcp

    az-ka
    F
    license
    Not graded
    quality
    D
    maintenance
    A local MCP server that turns AI clients into power users of local git repositories, enabling clone, browse, search, and inspect code without burning API tokens.
    -

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pluto-atom-4/mcp-gh-forge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server