Index codebases into MCP knowledge graphs with codebase-memory-mcp
Give coding agents a local MCP code intelligence graph for fast architecture, symbol, route, impact, and call-path queries across large repositories.
npx skills add agentskillexchange/skills --skill index-codebases-into-mcp-knowledge-graphs-with-codebase-memory-mcp
npm install -g codebase-memory-mcp, restart the MCP-compatible coding agent, then index the project before asking the agent architecture, symbol, route, impact, or call-path questions.Use codebase-memory-mcp when a coding agent needs structural codebase memory before planning or editing a large repository. The operator installs the MCP server, indexes the project into a local knowledge graph, and lets the agent query architecture, symbols, routes, impact analysis, dead code, and call paths instead of repeatedly reading files by hand. Invoke this for code exploration and change planning inside agent clients; the scope is local code intelligence through MCP, not a generic search engine, hosted repository viewer, or broad developer platform.
What this skill actually does
Inputs and prerequisites: MCP-compatible coding agent, codebase-memory-mcp binary or npm package, local repository access.
Setup notes: Install with the upstream setup script or `npm install -g codebase-memory-mcp`, restart the MCP-compatible coding agent, then index the project before asking the agent architecture, symbol, route, impact, or call-path questions.
Source and verification boundary: use https://github.com/DeusData/codebase-memory-mcp as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.