godoctor

GoDoctor

GoDoctor is an intelligent, AI-powered Model Context Protocol (MCP) server designed to assist Go developers. It provides a comprehensive suite of tools for navigating, editing, analyzing, and modernizing Go codebases.

Features

GoDoctor organizes its capabilities into domain-specific tools to streamline development workflows.

🔍 Navigation & Discovery

• list_files: Explore the project hierarchy recursively to understand the architecture.
• smart_read: The Universal Reader. Inspects file content, structure (outline), or specific snippets. Includes documentation for imported packages.

✏️ Smart Editing

• file_create: Initialize a new source file with proper boilerplate and import organization.
• smart_edit: Perform targeted code modifications using Levenshtein distance matching. Automatically handles formatting and checks syntax before finalizing.

🛠️ Go Toolchain Integration

• smart_build: The Universal Quality Gate. Compiles the project, runs tests, and checks for linting issues in a single atomic step. Automatically runs go mod tidy and gofmt.
• add_dependency: Manage module dependencies and immediately fetch documentation for the new package.
• read_docs: Query documentation for any package or symbol in the Go ecosystem.
• modernize_code: Automatically upgrade legacy Go patterns to modern standards.

🤖 Expert Assistance

• code_review: Submit code for expert AI analysis focusing on correctness and idiomatic style.

Installation

For Claude Code Users

1. Install the binary:

   go install github.com/danicat/godoctor/cmd/godoctor@latest
   

2. Add GoDoctor as an MCP server:

   claude mcp add --transport stdio --scope user godoctor -- godoctor
   

3. (Optional) Add agent instructions to your project:

   godoctor --agents >> CLAUDE.md
   

   This appends tool usage guidance to your CLAUDE.md so Claude knows how to use each tool effectively.

For Gemini CLI Users

If you use the Gemini CLI, you can install GoDoctor as an extension:

gemini extensions install https://github.com/danicat/godoctor

From Source

1. Clone the repository:

   git clone https://github.com/danicat/godoctor.git
   cd godoctor
   

2. Build and install:

   make install
   

Configuration

1. Authentication (Optional)

Most GoDoctor tools work without any authentication. The code_review tool requires access to Google's Generative AI models for cross-model code review. If no credentials are found, code_review is automatically disabled and all other tools continue to work normally.

Option 1: Gemini API (Personal) Set the GEMINI_API_KEY (or GOOGLE_API_KEY) environment variable.

export GEMINI_API_KEY="your-api-key"

Option 2: Vertex AI (Enterprise) Set the following environment variables:

export GOOGLE_GENAI_USE_VERTEXAI=true
export GOOGLE_CLOUD_PROJECT="your-project-id"
export GOOGLE_CLOUD_LOCATION="us-central1"

2. Command-Line Flags

Agent Integration

To get the optimal system prompt for your AI agent:

godoctor --agents

To see which tools are currently active:

godoctor --list-tools

License

Apache 2.0

Cloud Deployment

GoDoctor can be deployed as a containerized service on Google Cloud Run. This allows you to host your own MCP server instance securely.

Prerequisites

1. Google Cloud Project: You need an active GCP project.
2. gcloud CLI: Installed and authenticated (gcloud auth login).
3. Permissions:
   • Artifact Registry Administrator
   • Cloud Run Admin
   • Secret Manager Admin (if using Gemini API keys)
   • Vertex AI User (if using Vertex AI)

1. Setup Infrastructure

Run the setup script once to enable required APIs (Cloud Run, Artifact Registry, Secret Manager) and create the Docker repository.

# Optional: Set region (defaults to us-central1)
export GOOGLE_CLOUD_LOCATION="europe-west1"

./deploy/setup.sh

2. Deploy to Cloud Run

The deployment script handles building the container, pushing it to the registry, and deploying the service. It supports three modes:

Option A: Standard Mode (No AI)

Deploys the server with basic file and Go tools. The code_review tool will be disabled.

./deploy/deploy.sh

Option B: With Gemini API (Secret Manager)

For secure API key management, store your key in Secret Manager first:

echo -n "YOUR_API_KEY" | gcloud secrets create GEMINI_API_KEY --data-file=-

Then deploy with the Gemini flag. The script will securely mount the secret as an environment variable.

./deploy/deploy.sh --with-gemini

Option C: With Vertex AI

Uses your project's default Vertex AI quota.

./deploy/deploy.sh --with-vertex

3. Usage

After deployment, the script outputs the Service URL. You can connect your MCP client to this URL (e.g., using Streamable HTTP transport).

MCP Endpoint (Streamable HTTP): https://godoctor-xyz.a.run.app