Knowledge Graph Integration

Overview

Transform any codebase into a queryable knowledge graph using codebase-memory MCP server. Instead of reading entire files, query the graph for exactly the context you need.

Token savings: 6-71x reduction compared to raw file reading.

Setup

Prerequisites

• codebase-memory MCP server installed (~/bin/codebase-memory-mcp or via npm)
• MCP config in ~/.mcp.json:

{
  "mcpServers": {
    "codebase-memory": {
      "command": "/path/to/codebase-memory-mcp",
      "args": []
    }
  }
}

Core Operations

1. Index a Repository

mcp__codebase-memory__index_repository
  project_name: "my-project"
  repo_path: "/path/to/repo"

First index takes 30-120s depending on repo size. Subsequent updates are incremental.

2. Check Index Status

mcp__codebase-memory__index_status
  project_name: "my-project"

3. Search Code

mcp__codebase-memory__search_code
  project_name: "my-project"
  query: "authentication middleware"

Returns relevant code snippets without reading entire files.

4. Get Architecture Overview

mcp__codebase-memory__get_architecture
  project_name: "my-project"

Returns high-level architecture: modules, dependencies, entry points.

5. Trace Call Paths

mcp__codebase-memory__trace_call_path
  project_name: "my-project"
  from_symbol: "handleLogin"
  to_symbol: "validateToken"

6. Query Dependency Graph

mcp__codebase-memory__query_graph
  project_name: "my-project"
  query: "what depends on auth module?"

When to Use

Integration with Agents

code-reviewer

Before reviewing, query the graph for the blast radius of changes:

search_code("functions that call {changed_function}")

architect

Get architecture overview before proposing changes:

get_architecture("project")

sleuth

Trace call paths to understand bug propagation:

trace_call_path("buggy_function", "entry_point")

Token Savings Examples