Ast Metrics

Created By

Halleck454 months ago

Static code analyzer with MCP server. Gives AI agents access to complexity metrics, coupling analysis, community detection, risk scoring, and test quality, without reading every file.

# static-analysis

Overview Content Tools Comments

Overview

AST Metrics is a multi-language static code analyzer (Go, PHP, Python, Rust, TypeScript...) that exposes architectural insights via MCP. AI coding agents can query complexity hotspots, dependency graphs, coupling metrics, architectural communities, and test quality on demand.

No server required. No account. One binary. Works offline.

Tools exposed

analyze_project -- High-level project overview: languages, average complexity, maintainability, top risks
get_file_metrics -- Detailed metrics for a specific file (complexity, LOC, coupling, maintainability)
find_risky_code -- Ranked list of riskiest files/classes (composite score: complexity + coupling + change frequency)
find_complex_code -- Functions/classes above a cyclomatic complexity threshold
get_dependencies -- Dependency subgraph around a component
get_coupling -- Afferent and efferent coupling for a component
get_communities -- Architectural community detection with modularity metrics
get_test_quality -- Test isolation, traceability, god tests, orphan classes

Installation

curl -s https://raw.githubusercontent.com/Halleck45/ast-metrics/main/scripts/download.sh|bash

Configuration

Add to .mcp.json:

{
  "mcpServers": {
    "ast-metrics": {
      "command": "ast-metrics",
      "args": ["mcp", "."]
    }
  }
}

Try in Playground

Server Config

{
  "mcpServers": {
    "ast-metrics": {
      "command": "ast-metrics",
      "args": [
        "mcp",
        "."
      ]
    }
  }
}

Project Info

Created At

4 months ago

Updated At

4 months ago

Author Name

Halleck45

Star

-

Language

-

License

-

Category

Tags

static-analysis

Homepage

https://github.com/Halleck45/ast-metrics

Recommend Servers

Latvia Payments Mcp

@junter1989k-ai

11 days ago

Slovenia Payments Mcp

@junter1989k-ai

11 days ago

11 days ago

Kenya Payments Mcp

@junter1989k-ai

12 days ago

Language models generate; Concordance verifies. The verify tool checks a claim deterministically (no model in the loop) and returns HOLDS / BROKEN / INCOMPLETE with the worked reasoning and a sealed receipt (content_hash + cite_url) that re-fetches byte-identical or not at all. Also: ranked search over an ~11k-record library, seal_fetch to re-verify any receipt, redact to strip PII before text travels, and a sealed connection graph. Runs sovereign/offline too (stdlib-first Python). A public false-positive benchmark covers every domain: the engine has never sealed a falsehood. 38 tools live; remote endpoint at https://narrowhighway.com/mcp.

12 days ago

Tanzania Payments Mcp

@junter1989k-ai

11 days ago

Switzerland Payments Mcp

@junter1989k-ai

11 days ago

Slovakia Payments Mcp

@junter1989k-ai

11 days ago

Persistent Adaptive Planning Intelligence - structured loop engineering for AI coding assistants, with memory that persists across sessions, tools, and teammates.

12 days ago

ContextBridge (CB) is a local-first retrieval layer that sits between your codebase and your AI coding agent. Instead of pasting raw source files into context or letting the AI guess which files matter, CB indexes your codebase's real structure (via Graphify) and returns a compact, ranked result — owner file, related files, key symbols, and dependency chains — grounded in your actual code. A typical response is ~4–8 KB instead of the 100+ KB of raw source an AI would otherwise need to read to answer the same question — roughly a 96% cut in input tokens sent to your cloud AI, with zero hallucinated file paths or method names.

12 days ago

Ireland Payments Mcp

@junter1989k-ai

11 days ago

Romania Payments Mcp

@junter1989k-ai

11 days ago

Hungary Payments Mcp

@junter1989k-ai

11 days ago

Sweden Payments Mcp

@junter1989k-ai

11 days ago

Lithuania Payments Mcp

@junter1989k-ai

11 days ago

Jordan Payments Mcp

@junter1989k-ai

11 days ago

12 days ago

Israel Payments Mcp

@junter1989k-ai

11 days ago

Portugal Payments Mcp

@junter1989k-ai

11 days ago

Austria Payments Mcp

@junter1989k-ai

11 days ago

Uae Payments Mcp

@junter1989k-ai

12 days ago

Zhipu Web Search

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

a year ago

Qatar Payments Mcp

@junter1989k-ai

11 days ago

Algeria Payments Mcp

@junter1989k-ai

11 days ago

Pakistan Payments Mcp

@junter1989k-ai

11 days ago

Playwright MCP server

TypeScript

a year ago

Spain Payments Mcp

@junter1989k-ai

11 days ago

Malta Payments Mcp

@junter1989k-ai

11 days ago

Cyprus Payments Mcp

@junter1989k-ai

11 days ago

高德地图官方 MCP Server

a year ago