Gitrama Mcp

SSE

by ahmaxdev

327 downloads Not rated yet

GitHub Website

About

AI Git workflow MCP server. Generates conventional commit messages, branch names, PR descriptions, and manages work streams (wip, hotfix, review, experiment). Works with Cursor, Claude Desktop, Claude Code, Windsurf, and VS Code. Install: pip install gitrama-mcp

Details

Transport: SSE

Explore

- 10 tools across 5 intelligence domains
- Commit, branch, PR, stream, and repo automation
- Works with popular AI‑powered coding clients
- Simple Python package installation
- AI‑driven Git workflow assistance

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Gitrama Mcp

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

From the repository

Install it via pip install gitrama-mcp. It works with supported AI clients such as Cursor, Claude Desktop, Claude Code, Windsurf, VS Code, and Zed. No additional configuration details are provided in the README.

`gitrama_commit`

Generate an AI-powered commit message for currently staged changes. Analyzes the git diff of staged files and produces a conventional commit message following best practices. Requires files to be staged first (git add). Args: message: Optional custom commit message. If provided, skips AI generation and uses this message directly.

`gitrama_stage_and_commit`

Stage files and create an AI-powered commit in one step. Equivalent to `git add <files> && gtr commit -y`. Stages the specified files (or all changes), then generates and applies an AI commit message. Args: files: Files to stage — "." for all changes (default), or space-separated paths (e.g., "src/auth.py tests/test_auth.py"). message: Optional custom commit message. If provided, skips AI generation and uses this message directly.

`gitrama_ask`

Ask a natural language question about your repository. Uses Gitrama intelligence to provide context-aware answers. Example questions: - "Who owns the auth module?" - "Who are the top contributors?" - "When did we last change the payment logic?" - "What's the riskiest file in this repo?" - "What changed in the last 3 days?" - "Explain the purpose of src/utils/retry.py" - "What stream am I on?" Args: question: Natural language question about yo…

`gitrama_branch`

Generate an AI-powered branch name from a description. Analyzes your description and generates a conventional branch name following best practices (feat/, fix/, chore/, etc.), then optionally creates and switches to the branch. Examples: - "Add user authentication" → feat/add-user-authentication - "Fix memory leak" → fix/memory-leak - "Update docs" → docs/update-docs Args: description: What you're working on (e.g., "add user authentication …

`gitrama_pr`

Generate an AI-powered pull request description. Analyzes the diff between the current branch and the base branch, then generates a comprehensive PR description with title, summary, changes list, and testing notes. Args: base: Target branch for the PR (default: main or master).

`gitrama_stream_status`

Show the current Gitrama stream (workflow context). Streams are Gitrama's concept of workflow focus — they track what you're working on and influence AI suggestions. Returns the active stream name, description, and associated branch.

`gitrama_stream_switch`

Switch to a different Gitrama stream (workflow context). Creates a new stream or switches to an existing one. Streams help the AI understand what you're working on for better suggestions. Args: name: Stream name (e.g., "auth-refactor", "payment-v2"). description: Optional description of the stream's purpose.

`gitrama_stream_list`

List all Gitrama streams in the current repository. Shows all defined streams with their names, descriptions, and associated branches. The active stream is highlighted.

`gitrama_health`

Check the Gitrama AI server health status. Verifies connectivity to the Gitrama AI API and returns the current server status and MCP server version. Useful for diagnosing issues when other commands fail.

`gitrama_status`

Show the working tree status with AI interpretation. Displays the current git status including staged, unstaged, and untracked files with AI-powered context about the changes.

`gitrama_diff`

Show a risk-annotated diff of current changes. Overlays Gitrama's structural intelligence on top of the raw git diff — risk scores, churn rates, coupling gaps, and contributor context for every changed file. Opens a browser panel with the full analysis. Args: target: Branch or commit to diff against (default: working tree). staged: If True, diff staged changes only (default: all changes).

`gitrama_review`

Run an AI code review on current changes before committing. Sends your diff and repo intelligence to Gitrama's review engine. Returns severity-graded findings — security, correctness, risk, coupling — plus a verdict and suggested commit message. Runs before you push, not after. Catches issues at the right time. Args: mode: Review scope — one of: "staged" — staged changes only (default) "uncommitted" — all uncommitted changes …

`gitrama_unstage`

Remove files from the staging area without discarding changes. Moves files out of the git index back to the working tree. Changes are preserved — nothing is lost. Args: files: Space-separated file paths to unstage. Leave empty for interactive selection (CLI only). all_files: If True, unstage everything currently staged.

`gitrama_scan`

Run a full structural health scan of the repository. Scores every file for continuity risk, boundary entropy, and recurrence patterns. Identifies coupling hotspots and contributor concentration before they compound into failures. Results are cached in last_scan.json for use by gtr diff and gtr review.

`gitrama_push`

Push the current branch to a remote repository. Pushes committed changes to the specified remote. Optionally sets the upstream tracking branch for new branches. Args: remote: Remote to push to (default: "origin"). branch: Branch to push (default: current branch). force: If True, force push with --force-with-lease (safer than --force). set_upstream: If True, sets the upstream tracking branch (-u flag). Use this when pushing a …

Commit Intelligence — gitrama_commit, gitrama_stage_and_commit, gitrama_status

Branch Intelligence — gitrama_branch

PR Intelligence — gitrama_pr

Stream Intelligence — gitrama_stream_status, gitrama_stream_switch, gitrama_stream_list

Repo Intelligence — gitrama_ask, gitrama_health

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "gitrama mcp": {
            "gitrama-mcp": {
                "command": "gitrama-mcp",
                "args": [],
                "env": {
                    "GITRAMA_TOKEN": "your-token-here"
                }
            }
        }
    }
}

McpServers

{
    "gitrama-mcp": {
        "command": "gitrama-mcp",
        "args": [],
        "env": {
            "GITRAMA_TOKEN": "your-token-here"
        }
    }
}

AI Git workflow MCP server by Gitrama. Exposes 10 tools across 4 domains:

Tools

Commit Intelligence — gitrama_commit, gitrama_stage_and_commit, gitrama_status Branch Intelligence — gitrama_branch PR Intelligence — gitrama_pr Stream Intelligence — gitrama_stream_status, gitrama_stream_switch, gitrama_stream_list Repo Intelligence — gitrama_ask, gitrama_health

Install

pip install gitrama-mcp

Supported Clients

Cursor, Claude Desktop, Claude Code, Windsurf, VS Code, Zed

Links

- Website: https://gitrama.io - GitHub: https://github.com/ahmaxdev/gitrama-mcp - PyPI: https://pypi.org/project/gitrama-mcp/

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

gitrama_commit

gitrama_stage_and_commit

gitrama_ask

gitrama_branch

gitrama_pr

gitrama_stream_status

gitrama_stream_switch

gitrama_stream_list

gitrama_health

gitrama_status

gitrama_diff

gitrama_review

gitrama_unstage

gitrama_scan

gitrama_push

Claude Desktop / Cursor

McpServers

Tools

Install

Supported Clients

Links

More like this

Sentry

Github

Git

GitLab

`gitrama_commit`

`gitrama_stage_and_commit`

`gitrama_ask`

`gitrama_branch`

`gitrama_pr`

`gitrama_stream_status`

`gitrama_stream_switch`

`gitrama_stream_list`

`gitrama_health`

`gitrama_status`

`gitrama_diff`

`gitrama_review`

`gitrama_unstage`

`gitrama_scan`

`gitrama_push`