Context7 Documentation MCP Server with a Gemini Agent

## Main MCP Server Workflow Overview This workflow acts as the public gateway for the Context7 AI Documentation Agent. 1. Context7 MCP Server Trigger: * Receives requests from external clients (e.g., Roo Code, Cline) at its unique SSE endpoint URL. * The path is intentionally long and random for basic access control. * Client JSON for Roo Code etc.: "n8n-context7": { "url": "https://n8n.coolify.au/mcp/YOUR_LONG_RANDOM_PATH/sse", "alwaysAllow": [ "call_context7_ai_agent" // This is the tool name defined in the Tool Workflow node ] } (Replace YOUR_LONG_RANDOM_PATH with the actual path from the trigger node) 2. call_context7_ai_agent (Tool Workflow Node): * This is the "tool" the MCP Server Trigger exposes. * It calls the separate AI Agent Sub-Workflow (ID: vqujIu65SFbZUz0n), passing the user's query. Data Flow: External Client -> MCP Server Trigger -> call_context7_ai_agent (Tool) -> AI Agent Sub-Workflow -> (Response Stream) -> MCP Server Trigger -> External Client 3. There is a video I've made on youtube that explains this workflow a bit and why I created it: https://youtu.be/dudvmyp7Pyg?si=N59DYTe2WE6GPlvf