A modern, cross-platform Model Context Protocol (MCP) server that enables AI assistants to browse and interact with both Gopher protocol and Gemini protocol resources safely and efficiently. The Gopher & Gemini MCP Server bridges vintage and modern alternative internet protocols with AI assistants, allowing LLMs like Claude to explore the unique content and communities that thrive on both Gophersp
Add this skill
npx mdskills install cameronrye/gopher-mcpWell-documented MCP server enabling AI access to Gopher and Gemini protocols with robust security features
A modern, cross-platform Model Context Protocol (MCP) server that enables AI assistants to browse and interact with both Gopher protocol and Gemini protocol resources safely and efficiently.
The Gopher & Gemini MCP Server bridges vintage and modern alternative internet protocols with AI assistants, allowing LLMs like Claude to explore the unique content and communities that thrive on both Gopherspace and Geminispace. Built with FastMCP and modern Python practices, it provides secure, efficient gateways to these distinctive internet protocols.
Key Benefits:
gopher_fetch and gemini_fetch tools for comprehensive protocol coverageComplete documentation is available at cameronrye.github.io/gopher-mcp
# Clone the repository
git clone https://github.com/cameronrye/gopher-mcp.git
cd gopher-mcp
# Set up development environment
./scripts/dev-setup.sh # Unix/macOS
# or
scripts\dev-setup.bat # Windows
# Run the server
uv run task serve
# Install from PyPI (recommended for end users)
pip install gopher-mcp
# Or with uv
uv add gopher-mcp
# Install directly from GitHub
uv add git+https://github.com/cameronrye/gopher-mcp.git
# Or install in development mode
git clone https://github.com/cameronrye/gopher-mcp.git
cd gopher-mcp
uv sync --all-extras
Add to your claude_desktop_config.json:
Unix/macOS/Linux:
{
"mcpServers": {
"gopher": {
"command": "uv",
"args": ["--directory", "/path/to/gopher-mcp", "run", "task", "serve"],
"env": {
"MAX_RESPONSE_SIZE": "1048576",
"TIMEOUT_SECONDS": "30"
}
}
}
}
Windows:
{
"mcpServers": {
"gopher": {
"command": "uv",
"args": [
"--directory",
"C:\\path\\to\\gopher-mcp",
"run",
"task",
"serve"
],
"env": {
"MAX_RESPONSE_SIZE": "1048576",
"TIMEOUT_SECONDS": "30"
}
}
}
}
This project includes a unified Python-based task management system that works across all platforms:
python task.py # Unified Python task runner (recommended)
# Unix/macOS/Linux
make # Traditional make (delegates to task.py)
# Universal fallback
uv run task # Direct taskipy usage
| Command | Description |
|---|---|
dev-setup | Set up development environment |
install-hooks | Install pre-commit hooks |
lint | Run ruff linting |
format | Format code with ruff |
typecheck | Run mypy type checking |
quality | Run all quality checks |
check | Run lint + typecheck |
test | Run all tests |
test-cov | Run tests with coverage |
test-unit | Run unit tests only |
test-integration | Run integration tests |
serve | Run MCP server (stdio) |
serve-http | Run MCP server (HTTP) |
docs-serve | Serve docs locally |
docs-build | Build documentation |
clean | Clean build artifacts |
ci | Run CI pipeline locally |
The server provides two powerful MCP tools for exploring alternative internet protocols:
gopher_fetch ToolFetches Gopher menus, text files, or metadata by URL with comprehensive error handling and security safeguards.
Parameters:
url (string, required): Full Gopher URL (e.g., gopher://gopher.floodgap.com/1/)Response Types:
gemini_fetch ToolFetches Gemini content with full TLS security, TOFU certificate validation, and native gemtext parsing.
Parameters:
url (string, required): Full Gemini URL (e.g., gemini://geminiprotocol.net/)Response Types:
# Classic Gopher menu
gopher://gopher.floodgap.com/1/
# Gopher news and information
gopher://gopher.floodgap.com/1/gopher
# Search example (type 7)
gopher://gopher.floodgap.com/7/v2/vs
# Text file example
gopher://gopher.floodgap.com/0/gopher/welcome
# Gemini protocol homepage
gemini://geminiprotocol.net/
# Gemini software directory
gemini://geminiprotocol.net/software/
# Example personal gemlog
gemini://warmedal.se/~antenna/
# Gemini search aggregator
gemini://kennedy.gemi.dev/
Once configured, you can ask Claude:
Gopher Exploration:
Gemini Exploration:
gopher-mcp/
├── src/gopher_mcp/ # Main package
│ ├── __init__.py # Package initialization
│ ├── server.py # FastMCP server implementation
│ ├── gopher_client.py # Gopher protocol client
│ ├── models.py # Pydantic data models
│ ├── tools.py # MCP tool definitions
│ └── utils.py # Utility functions
├── tests/ # Comprehensive test suite
│ ├── test_server.py # Server tests
│ ├── test_gopher_client.py # Client tests
│ └── test_integration.py # Integration tests
├── docs/ # MkDocs documentation
├── scripts/ # Development scripts
├── .github/workflows/ # CI/CD pipelines
├── Makefile # Unix/macOS task runner
├── task.bat # Windows task runner
└── pyproject.toml # Modern Python project config
uv run task dev-setup - Install dependencies and pre-commit hooksuv run task quality - Run all quality checks (lint + typecheck + test)uv run task test-cov - Run tests with coverage reporting# Run all tests
uv run task test
# Run with coverage
uv run task test-cov
# Run specific test types
uv run task test-unit
uv run task test-integration
# Run tests in watch mode during development
uv run pytest --watch
The server can be configured through environment variables for both protocols:
| Variable | Description | Default | Example |
|---|---|---|---|
GOPHER_MAX_RESPONSE_SIZE | Maximum response size in bytes | 1048576 (1MB) | 2097152 |
GOPHER_TIMEOUT_SECONDS | Request timeout in seconds | 30 | 60 |
GOPHER_CACHE_ENABLED | Enable response caching | true | false |
GOPHER_CACHE_TTL_SECONDS | Cache time-to-live in seconds | 300 | 600 |
GOPHER_ALLOWED_HOSTS | Comma-separated allowed hosts | None (all) | example.com,test.com |
| Variable | Description | Default | Example |
|---|---|---|---|
GEMINI_MAX_RESPONSE_SIZE | Maximum response size in bytes | 1048576 (1MB) | 2097152 |
GEMINI_TIMEOUT_SECONDS | Request timeout in seconds | 30 | 60 |
GEMINI_CACHE_ENABLED | Enable response caching | true | false |
GEMINI_CACHE_TTL_SECONDS | Cache time-to-live in seconds | 300 | 600 |
GEMINI_ALLOWED_HOSTS | Comma-separated allowed hosts | None (all) | example.org,test.org |
GEMINI_TOFU_ENABLED | Enable TOFU certificate validation | true | false |
GEMINI_CLIENT_CERTS_ENABLED | Enable client certificate support | true | false |
# Gopher settings
export GOPHER_MAX_RESPONSE_SIZE=2097152
export GOPHER_TIMEOUT_SECONDS=60
export GOPHER_CACHE_ENABLED=true
export GOPHER_ALLOWED_HOSTS="gopher.floodgap.com,gopher.quux.org"
# Gemini settings
export GEMINI_MAX_RESPONSE_SIZE=2097152
export GEMINI_TIMEOUT_SECONDS=60
export GEMINI_TOFU_ENABLED=true
export GEMINI_CLIENT_CERTS_ENABLED=true
export GEMINI_ALLOWED_HOSTS="geminiprotocol.net,warmedal.se"
# Run with custom config
uv run task serve
We welcome contributions! Please see our Contributing Guidelines for details.
git clone https://github.com/your-username/gopher-mcp.gituv run task dev-setupgit checkout -b feature/amazing-featureuv run task qualitygit commit -m 'Add amazing feature'git push origin feature/amazing-featureThis project is licensed under the MIT License - see the LICENSE file for details.
Made with ❤️ by Cameron Rye
Star this project if you find it useful!
Install via CLI
npx mdskills install cameronrye/gopher-mcpGopher & Gemini MCP Server is a free, open-source AI agent skill. A modern, cross-platform Model Context Protocol (MCP) server that enables AI assistants to browse and interact with both Gopher protocol and Gemini protocol resources safely and efficiently. The Gopher & Gemini MCP Server bridges vintage and modern alternative internet protocols with AI assistants, allowing LLMs like Claude to explore the unique content and communities that thrive on both Gophersp
Install Gopher & Gemini MCP Server with a single command:
npx mdskills install cameronrye/gopher-mcpThis downloads the skill files into your project and your AI agent picks them up automatically.
Gopher & Gemini MCP Server works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Gemini Cli, Amp, Roo Code, Goose. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.