codebase-memory-mcp MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Indexes 66 languages via tree-sitter — Linux kernel in 3 minutes
14 MCP tools for graph queries, call tracing, architecture overview, and code search
~99% token reduction vs file-by-file exploration
Single static binary, zero runtime dependencies (macOS, Linux, Windows)
Optional 3D graph visualization UI at localhost:9749

Live-Demo

In der Praxis

codebase-memory.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "codebase-memory": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/DeusData/codebase-memory-mcp"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "codebase-memory": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/DeusData/codebase-memory-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "codebase-memory": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/DeusData/codebase-memory-mcp"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "codebase-memory": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/DeusData/codebase-memory-mcp"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "codebase-memory",
      "command": "TODO",
      "args": [
        "See README: https://github.com/DeusData/codebase-memory-mcp"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "codebase-memory": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/DeusData/codebase-memory-mcp"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add codebase-memory -- TODO 'See README: https://github.com/DeusData/codebase-memory-mcp'

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: codebase-memory-mcp

How to quickly understand a new codebase with codebase-memory

👤 Developers onboarding onto an unfamiliar project ⏱ ~15 min beginner

Wann einsetzen: You just joined a team or started working on a new repo and need to understand its architecture fast.

Voraussetzungen

codebase-memory installed — curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash

Ablauf

Index the codebase

Index this project repository and give me an architecture overview.✓ Kopiert

→ High-level module map with key entry points and dependencies
Explore a specific module

Show me the call graph for the authentication module. What functions does login() call?✓ Kopiert

→ Call chain from login through middleware, validation, and database
Find related code

Search the graph for all functions that interact with the user table.✓ Kopiert

→ List of functions with file locations and relationships

Ergebnis: A solid mental model of the codebase architecture in minutes instead of hours.

Fallstricke

Indexing very large monorepos takes time on first run — Use index_status to check progress. Subsequent queries are instant since the graph persists.

Kombinieren mit: filesystem · github

Analyze the impact of a code change before refactoring

👤 Senior engineers planning a refactoring effort ⏱ ~20 min intermediate

Wann einsetzen: You want to know what will break before you rename, move, or delete a function or class.

Voraussetzungen

Codebase indexed — Run index_repository first

Ablauf

Trace all callers

Trace all call paths to the deprecated processPayment() function across the entire codebase.✓ Kopiert

→ Complete list of callers with file paths and call depths
Map git changes to symbols

I changed these files in my branch. Use detect_changes to show which symbols in the graph are affected.✓ Kopiert

→ List of affected functions and their downstream dependents

Ergebnis: A complete impact analysis showing all code that needs to change.

Fallstricke

Graph may be stale if code changed since last index — Re-run index_repository after significant code changes

Kombinieren mit: github · filesystem

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

codebase-memory + github

Index a repo, then use GitHub MCP to find PRs that affect critical call paths

Index our repo, trace all callers of the auth middleware, then check if any open PRs modify those paths.✓ Kopiert

codebase-memory + filesystem

Index locally, query the graph, then edit the found files directly

Find all functions that call the deprecated API, then update each one to use the new API.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen
index_repository	path: str	Index a codebase into the knowledge graph (run once, persists)
search_graph	label?: str, pattern?: str	Search the graph by label or pattern
trace_call_path	from: str, to: str	Find call chains between two functions
detect_changes	diff: str	Map git diffs to affected symbols in the graph
get_architecture	project?: str	Get a high-level architecture overview of the indexed codebase
query_graph	query: str	Run a Cypher-like query against the graph
search_code	pattern: str	Grep-style text search across indexed code

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: N/A — fully local
Tokens pro Aufruf: 50–500 tokens per query (vs 2000+ for reading files directly)
Kosten in €: Free
Tipp: Index once, query many times. The graph persists between sessions so you don't re-index.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: N/A — no external credentials

Datenabfluss: 100% local processing. Your code never leaves your machine.

Binaries are verified via VirusTotal (70+ engines), SLSA Level 3 provenance, Sigstore signatures, and SHA-256 checksums.

Fehlerbehebung

Häufige Fehler und Lösungen

Indexing fails on large repo

Ensure sufficient disk space for the graph database. For very large repos (>1M LOC), first indexing may take several minutes.

Prüfen: Check index_status for progress

Language not parsed correctly

Verify your language is in the 66 supported languages. Check tree-sitter grammar availability.

Prüfen: list_projects to see indexed stats

Graph queries return empty results

The codebase may not be indexed yet. Run index_repository first, then wait for completion.

Prüfen: index_status

Alternativen

codebase-memory-mcp vs. andere

Alternative	Wann stattdessen	Kompromiss
filesystem MCP	You just need to read specific files rather than understand the whole codebase	No graph, no call tracing — but zero setup

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen