MCP Catalogs
Homearbor screenshot

arbor

by Anandb71·117·Score 49

A graph-native code intelligence tool with 10 MCP tools for analyzing code dependencies and impact.

developer-toolsai-llmknowledge-graph
18
Forks
2
Open issues
this month
Last commit
2d ago
Indexed

Overview

Arbor is a code intelligence tool that builds a semantic dependency graph for codebases, replacing embedding-based RAG with deterministic program understanding. It offers 10 MCP tools for surgical graph traversal and architectural analysis, allowing developers to understand the blast radius of changes before making them. The tool supports multiple programming languages and integrates with various interfaces including CLI, GUI, and MCP for AI models.

Try asking AI

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

you:Analyzing code impact before refactoring
you:Finding all callers and callees of a function
you:Blocking PRs with high architectural blast radius in CI/CD
you:Exploring code structure and dependencies visually
you:What programming languages does Arbor support?
you:How does Arbor differ from traditional RAG-based code analysis?
you:Can Arbor be used in CI/CD pipelines?

When to choose this

Choose Arbor when you need deterministic, explainable code impact analysis across language boundaries, especially for large codebases where understanding blast radius before changes is critical.

When NOT to choose this

Don't choose Arbor if you only work with small, single-language projects where the overhead of maintaining a dependency graph outweighs the benefits.

Tools this server exposes

10 tools extracted from the README
  • list_entry_points

    Lists entry points in the codebase

  • get_callers

    Gets all functions that call a specific symbol

  • get_callees

    Gets all functions called by a specific symbol

  • search_symbols

    Searches for symbols in the codebase

  • get_file_graph

    Gets the dependency graph for a specific file

  • get_node_detail

    Gets detailed information about a specific node in the graph

  • get_logic_path

    Gets the logical path between two symbols

  • analyze_impact

    Analyzes the impact of changing a specific symbol

  • find_path

    Finds a path between two symbols in the graph

  • get_knowledge_path

    Gets the knowledge path between symbols

Comparable tools

semgrep-mcpcode-mcptree-sitter-mcp

Installation

Installation

CLI Installation

# Rust / Cargo
cargo install arbor-graph-cli

# Homebrew (macOS/Linux)
brew install Anandb71/tap/arbor

# Scoop (Windows)
scoop bucket add arbor https://github.com/Anandb71/arbor
scoop install arbor

# Docker
docker pull ghcr.io/anandb71/arbor:latest

MCP Integration

claude mcp add --transport stdio --scope project arbor -- arbor bridge
claude mcp list

Initialize a Project

cd your-project
arbor setup

Usage

# See what a function impacts
arbor refactor <symbol-name>

# Check impact of uncommitted changes
arbor diff

# Launch GUI
arbor gui

FAQ

What programming languages does Arbor support?
Arbor supports production parsing and graph analysis across major ecosystems including Rust, TypeScript/JavaScript, Python, Go, Java, C/C++, C#, Dart, Kotlin, Swift, Ruby, PHP, and Shell.
How does Arbor differ from traditional RAG-based code analysis?
Arbor uses a semantic dependency graph and deterministic program understanding instead of embedding-based RAG, providing exact answers to questions like 'What breaks if I change this symbol?' instead of approximate keyword matches.
Can Arbor be used in CI/CD pipelines?
Yes, Arbor provides Git-aware risk gating with GitHub Actions and CLI commands like `arbor check --max-blast-radius` to automatically block PRs with dangerously high architectural impact.

On Hacker News

Recent discussion from the developer community.

Compare arbor with

GitHub →

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