Skip to content
MCP server

Fallow

Dead code, duplication and complexity analysis for TypeScript and JavaScript repos

Runs locallyStatus and history
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
3.43.2
Listing updated
3 days ago

About Fallow

Fallow is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Fallow builds a full module graph of a codebase so an agent can ask questions it cannot answer by reading files: which exports are unused, which dependencies are never imported, where clones sit and which files are complexity hotspots. The page stresses that results are deterministic and complete.

The CLI is the main interface, with JSON output and a changed-since filter for pull-request workflows. The MCP server is an optional stdio layer that gives the same analyses typed inputs and outputs. It runs most requests in process and starts the CLI for options only the CLI has.

It resolves export-star chains through barrel files and detects feature flags and environment gates. The npm package ships the fallow-mcp launcher.

Install

Run in a terminal

claude mcp add fallow -- npx -y fallow

Add to claude_desktop_config.json

{
  "mcpServers": {
    "fallow": {
      "command": "npx",
      "args": [
        "-y",
        "fallow"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "fallow": {
      "command": "npx",
      "args": [
        "-y",
        "fallow"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "fallow": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "fallow"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "fallow": {
      "command": "npx",
      "args": [
        "-y",
        "fallow"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "fallow": {
      "command": "npx",
      "args": [
        "-y",
        "fallow"
      ]
    }
  }
}

What it does

Module graph
Builds one cached import graph across thousands of files.
Dead code finder
Reports unused exports and dependencies.
Duplication detection
Finds clones across files with a suffix array.
Auto-fix preview
Dry-run before applying removals.
Typed output
JSON types for check, health, dupes and audit results.

Good for

  • Clean unused exports before a release
  • Check only files changed since main
  • Find duplicated code across a monorepo
  • Give a coding agent repeatable answers

Pricing

Open source

Prices change. Check fallow.tools before you buy.

Fallow FAQ

Do I need MCP?

No, any agent that runs shell commands can use the CLI.

Is output stable?

The page says the same input gives the same output.

How is it installed?

Through the fallow npm package, cargo, or release binaries.

Is Fallow free?

Yes. Fallow is open source, so you can use and self-host it for free.

How do I add Fallow to Claude Code?

Run this command in your terminal: claude mcp add fallow -- npx -y fallow

What are the best alternatives to Fallow?

The closest alternatives to Fallow are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Fallow

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools