CodeGraphContext

CodeGraphContext provides a Python CLI and an MCP server that index local source code into a graph database (e.g., KùzuDB default, FalkorDB, or Neo4j) and enables querying relationships like call chains, callers/callees, class hierarchies, and other code structure details for AI assistants and developers.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ Ai Ml ai-ml code-analysis mcp cli graph-database tree-sitter code-search static-analysis
⚙ Agent Friendliness
44
/ 100
Can an agent use this?
🔒 Security
47
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
75
Documentation
55
Error Messages
0
Auth Simplicity
60
Rate Limits
0

🔒 Security

TLS Enforcement
60
Auth Strength
55
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
65

Uses local database credentials (Neo4j URI/username/password) and mentions storing them in ~/.codegraphcontext/.env, which is better than hardcoding but still requires host filesystem protection. TLS enforcement for remote backends is not described in the provided content. No details are given about encryption at rest, secret redaction in logs, or fine-grained permission scopes.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
30
Error Recovery
35
AF Security Reliability

Best When

You want local, graph-based code understanding (especially for call graphs and code navigation) and you can run/manage a local graph DB backend.

Avoid When

You cannot safely store local indexing outputs/graph data or you need a fully documented, standardized API contract beyond MCP/CLI.

Use Cases

  • Index a local repository into a code knowledge graph for AI-assisted code understanding
  • Answer natural-language queries about code relationships (via MCP)
  • Static analysis tasks like dead-code detection, complexity analysis, and call-chain exploration
  • Incremental updates via directory watching during development
  • Load and analyze pre-indexed repository bundles (.cgc)

Not For

  • Running as a managed hosted service for remote codebases (it targets local code indexing)
  • Handling extremely sensitive environments without reviewing how credentials and data are stored
  • Replacing full IDE language services/linters for correctness-critical tasks

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Local configuration via env vars (e.g., NEO4J_URI/USERNAME/PASSWORD) or database credentials stored in ~/.codegraphcontext/.env
OAuth: No Scopes: No

No user-facing OAuth/API-key auth is described; authentication is primarily to the selected graph database backend through configured credentials.

Pricing

Free tier: No
Requires CC: No

No hosted pricing model is described; costs are primarily local compute/storage and any graph DB you run (e.g., Neo4j).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • The README indicates MCP server usage via CLI commands, but the quality of MCP tool schemas, error messages, and idempotency/retry behavior is not evidenced in the provided README excerpt.
  • Authentication/connection details appear to depend on local DB credentials; agents may need to ensure env/.env are set correctly before starting the MCP server.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for CodeGraphContext.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered