LAIN-mcp

LAIN builds a map of how all the code in your project connects — what calls what, what depends on what, which files tend to change together. Then it lets your AI coding assistant ask questions about that map. So instead of the AI just looking at one file and guessing, it can ask "if I change this function, what else breaks?" and get a real answer. It plugs into any AI agent that supports MCP and runs in the background while you work.

TL,DR:

# One-line install (interactive - will ask you to configure and add to PATH)
curl -fsSL https://raw.githubusercontent.com/spuentesp/lain/main/install.sh | bash

# After install: reload your shell (or open a new terminal)
source ~/.zshrc   # or ~/.bashrc

# Or non-interactive (skips prompts, auto-adds to PATH)
curl -fsSL https://raw.githubusercontent.com/spuentesp/lain/main/install.sh | \
  bash /dev/stdin --workspace . --transport both --yes

What is Lain?

Lain is a persistent code-intelligence MCP server. It builds a queryable knowledge graph of your codebase — symbols and their relationships extracted via LSP and tree-sitter, augmented with git co-change history and optional semantic embeddings — and exposes that graph through MCP tools. The value over LSP-only or RAG-based approaches is cross-file structural reasoning: blast radius for proposed changes, transitive dependency traces, anchor identification, co-change correlation, and contextual build failure decoration so agents can reason about callers rather than just the failing line. Written in Rust, persists across sessions, stays fresh during editing via a file watcher that updates a volatile overlay layered on top of the static graph.

Installation

Quick Install (recommended - interactive)

curl -fsSL https://raw.githubusercontent.com/spuentesp/lain/main/install.sh | bash

The installer will ask you to configure:

• Workspace path
• MCP transport mode (stdio, http, or both)
• HTTP port (if using http/both)
• Target agent (auto-detects Claude Code, Cursor, Windsurf, Cline)
• Whether to download the ONNX model for semantic search

After you confirm your settings, it will:

1. Download and install LAIN to ~/.local/lain
2. Optionally download the ONNX model (~120MB)
3. Run lain init with your configuration
4. Add LAIN to your agent's settings

Non-interactive install (with options):

# Install with specific workspace and download ONNX model for semantic search
curl -fsSL https://raw.githubusercontent.com/spuentesp/lain/main/install.sh | \
  bash /dev/stdin --workspace . --transport both --download-model --yes

# Install for specific agent
curl -fsSL https://raw.githubusercontent.com/spuentesp/lain/main/install.sh | \
  bash /dev/stdin --agent cursor --yes

# See all options
curl -fsSL https://raw.githubusercontent.com/spuentesp/lain/main/install.sh | \
  bash /dev/stdin --help

Install options:

After installation:

# Reload your shell (the installer adds to ~/.zshrc or ~/.bashrc automatically)
source ~/.zshrc   # or ~/.bashrc, then open a new terminal

# Verify installation
lain --version

# Query the graph
lain query "find Function | limit 5"

Homebrew

brew tap spuentesp/lain https://github.com/spuentesp/lain
brew install lain

# Initiali

... [View full README on GitHub](https://github.com/spuentesp/lain#readme)