MCP server that indexes codebases into a SQLite-backed code graph using tree-sitter parsing, semantic edges, overlays, and incremental hashing. It provides tools for symbol discovery/navigation, dependency and dataflow tracing, change impact review, architecture analysis, workspace auditing, and SCIP import/export.
From the registry: Deterministic layered code graph MCP server with framework overlays and SCIP interop.
$ npm i -g @levnikolaevich/hex-graph-mcphttps://www.npmjs.com/package/@levnikolaevich/hex-graph-mcpPlease install the `hex-graph-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js 20.19.0 or newer** — Node.js version 20.19.0 or higher is required to run this MCP server.
- **Install the hex-graph-mcp package globally** — Install the MCP server package so the `hex-graph-mcp` command is available on your system. Run: `npm i -g @levnikolaevich/hex-graph-mcp` (https://www.npmjs.com/package/@levnikolaevich/hex-graph-mcp)
Canonical MCP server config (stdio transport):
- command: `hex-graph-mcp`
- args: []
Note: The README states `server.mjs` uses stdio transport. Prefer the globally installed `hex-graph-mcp` command over the example local `node path/to/mcp/hex-graph-mcp/server.mjs` path because it is the simpler and more portable install method. No MCP-specific environment variables are documented.
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.