Skip to main content
Glama

Google Search MCP Server

by jspv
Dockerfile.mcp1.27 kB
# Containerized MCP Service Dockerfile FROM python:3.12-slim WORKDIR /app # Install system dependencies RUN apt-get update && apt-get install -y \ curl \ && rm -rf /var/lib/apt/lists/* # Install uv RUN pip install uv # Copy requirements and install Python dependencies COPY pyproject.toml uv.lock ./ RUN uv sync --frozen --extra container --extra http # Copy source code COPY server.py . COPY server_http.py . COPY server_http_stream.py . # Expose ports for different MCP modes EXPOSE 8000 8001 8002 # Default to HTTP streaming mode, but allow override ENV MCP_MODE=http-stream ENV HOST=0.0.0.0 ENV PORT=8000 # Create entrypoint script RUN echo '#!/bin/bash\n\ case "$MCP_MODE" in\n\ "stdio")\n\ echo "Starting MCP server in stdio mode..."\n\ exec uv run python server.py\n\ ;;\n\ "http")\n\ echo "Starting MCP server in HTTP mode on $HOST:$PORT..."\n\ exec uv run python server_http.py\n\ ;;\n\ "http-stream")\n\ echo "Starting MCP server in HTTP streaming mode on $HOST:$PORT..."\n\ exec uv run python server_http_stream.py\n\ ;;\n\ *)\n\ echo "Unknown MCP_MODE: $MCP_MODE. Use stdio, http, or http-stream"\n\ exit 1\n\ ;;\n\ esac' > /app/entrypoint.sh RUN chmod +x /app/entrypoint.sh ENTRYPOINT ["/app/entrypoint.sh"]

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/jspv/google_search_mcp'

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