code-graph-mcp

code-graph-mcp is a Python MCP server that builds and serves a multi-language code graph for code intelligence tasks (navigation/search for symbols, call graphs, dependency graphs, complexity/health metrics) using ast-grep with caching and a file-watcher for incremental updates.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ DevTools mcp code-analysis static-analysis call-graph dependency-graph complexity ast python
⚙ Agent Friendliness
65
/ 100
Can an agent use this?
🔒 Security
23
/ 100
Is it safe for agents?
⚡ Reliability
40
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
75
Documentation
70
Error Messages
0
Auth Simplicity
95
Rate Limits
0

🔒 Security

TLS Enforcement
0
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
70
Secret Handling
50

No authentication/authorization model is documented (appears designed for local use by an MCP host). The server indexes local code and logs/monitoring are mentioned, but the README does not describe logging redaction for secrets or safe handling of sensitive file contents. TLS/rate limiting are not applicable/undocumented for a local MCP server; security posture should be reviewed in the codebase.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
45
Error Recovery
60
AF Security Reliability

Best When

You have a local repository (possibly polyglot) and want an MCP-connected agent to navigate and analyze code structure, dependencies, and complexity efficiently.

Avoid When

You need authenticated multi-tenant remote access, or you cannot grant the MCP process read access to the project files.

Use Cases

  • Codebase exploration across multiple languages (25+)
  • Finding definitions and references for symbols in mixed-language repos
  • Generating caller/callee and dependency/circular dependency graphs
  • Assessing complexity and maintainability / project health
  • Detecting potential code smells (e.g., long functions, duplication patterns)
  • Architecture and refactoring impact analysis via tool workflows

Not For

  • Production deployment without reviewing runtime security and performance characteristics
  • Pure SaaS/API usage without a local/hosted MCP runtime
  • Tasks requiring authoritative semantic understanding beyond static analysis
  • Environments that forbid file system watchers or broad codebase indexing

Interface

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

Authentication

Methods: None described (local MCP server process)
OAuth: No Scopes: No

README describes local MCP host configuration and CLI usage but does not document authentication mechanisms, API keys, or scoped access control.

Pricing

Free tier: No
Requires CC: No

No hosted pricing described; distributed as a Python package (installation via pip/PyPI).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Server may re-analyze on file changes; repeated calls during active edits could trigger incremental indexing and higher latency.
  • Very large repositories may be expensive (tools labeled as expensive/moderate); agents should prefer the 'Fast' tools first.
  • ast-grep and caching assumptions may require sufficient CPU/RAM; environment misconfiguration (missing deps) will prevent proper graph building.

Alternatives

Full Evaluation Report

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

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