MCP Catalogs
Home

fossil-mcp

by yfedoseev·56·Score 45

Fossil MCP is a code quality toolkit that detects dead code, clones, and scaffolding in vibe-coded projects across 16 languages.

developer-toolsai-llm
4
Forks
3
Open issues
1 mo ago
Last commit
2d ago
Indexed

Overview

Fossil MCP is a specialized static analysis tool designed for AI-assisted codebases, addressing problems that traditional linters miss. It works both as a CLI tool and as an MCP server that provides AI agents with a code graph instead of text search capabilities. The tool detects dead code accumulating when AI rewrites functions, structural duplication across modules, scaffolding markers like TODO comments and placeholder functions, and temporary files that persist across sessions.

Try asking AI

After installing, here are 7 things you can ask your AI assistant:

you:Maintaining codebases written largely by AI agents where dead code accumulates
you:Detecting duplicated code that traditional similarity-based tools miss
you:Identifying scaffolding artifacts left by AI in production code
you:Providing AI agents with call graphs to understand code dependencies
you:Integrating code quality checks into CI/CD pipelines for AI-generated code
you:How does Fossil differ from traditional linters?
you:What languages does Fossil support?

When to choose this

Choose this if your development workflow relies heavily on AI coding assistants and you need to detect code quality issues that traditional linters miss in AI-generated code.

When NOT to choose this

Don't choose this if you need a general-purpose code quality tool or if your development workflow doesn't involve AI coding assistants.

Tools this server exposes

8 tools extracted from the README
  • scan_all

    Run all analyses (dead code + clones + scaffolding) on a project

  • analyze_dead_code

    Detect unreachable code with configurable confidence

  • detect_clones

    Find duplicated code (Type 1/2/3 clones)

  • fossil_refresh

    Incremental re-analysis after file changes (fast)

  • fossil_inspect

    Inspect call graph, data flow, control flow, or blast radius for any function

  • fossil_trace

    Find call paths between two functions — understand how code connects

  • fossil_explain_finding

    Get rich context about a specific finding

  • fossil_detect_scaffolding

    Find AI scaffolding: phased comments, TODOs, placeholders, and temp files

Comparable tools

semgrep-mcpsnyk-mcpcodeclimatesonarqubeeslint

Installation

Quick Install

**macOS/Linux:**

curl -fsSL fossil-mcp.com/install.sh | sh

**Windows (PowerShell):**

irm fossil-mcp.com/install.ps1 | iex

MCP Server Setup for Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "fossil": {
      "command": "fossil-mcp"
    }
  }
}

FAQ

How does Fossil differ from traditional linters?
Fossil is specifically designed for artifacts accumulated in AI-assisted coding, such as dead code from forgotten helper functions, structural duplication across modules, and scaffolding markers left by AI. It uses call graphs rather than text search to understand code connectivity.
What languages does Fossil support?
Fossil works across 16 programming languages including JavaScript/TypeScript, Python, Java, C/C++, Rust, Go, Ruby, PHP, C#, Swift, Kotlin, and more. It automatically detects and adapts to different language ecosystems.

On Hacker News

Recent discussion from the developer community.

Compare fossil-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.