sourcebook captures project knowledge that teams possess but is not present in the code, providing context for AI coding agents to improve their understanding and performance.
From the registry: Live codebase intelligence for AI agents: conventions, blast radius, import graphs, git insights.

Please install the `sourcebook` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js** — Node.js runtime required for npx (https://nodejs.org)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","sourcebook","serve","--dir","<path/to/your/project>"]
Note: Codebase intelligence MCP server. 8 tools: analyze_codebase, get_file_context, get_blast_radius, query_conventions, get_import_graph, get_git_insights, get_pressing_questions, search_codebase_context. No API keys or LLM required — fully deterministic local analysis.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.