Getting started

How it works

Dynvo is two pieces that share one artifact. The engine scans a repo and writes a feature-map JSON; the MCP server serves that JSON to your AI agent. Install both, scan once, point your editor at the MCP, and your agent stops guessing about your code.

Connect the MCP

The MCP is a hosted, OAuth-secured server — nothing to install. Point any MCP client at it through the standard mcp-remote bridge; the first run opens your browser to authorize:

npx -y mcp-remote https://app.dynvo.ai/api/mcp

Want to run the scanner locally too? The engine is a separate Python package — install it from PyPI:

pip install dynvo

Run a scan

Point the engine at any local repo. The full flag set emits coverage, flow participants, and classifications alongside the feature map:

dynvo analyze ~/my-project --llm --flows --symbols --trace-flows

The result lands at ~/.dynvo/feature-map-<slug>.json — the same artifact the MCP reads. After every push an incremental scan reruns in about 5 seconds for cents in LLM cost, so your agent's context never goes stale (PR branches get their own current scan, separate from main).

Connect your agent

Any MCP-compatible client works — Cursor, Claude Code, Cline, Aider, Continue. Drop the server into the client's MCP config and restart it. For Cursor that's ~/.cursor/mcp.json:

{
  "mcpServers": {
    "faultlines": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://app.dynvo.ai/api/mcp"]
    }
  }
}

Then ask your agent “what features touch checkout?” or “what's the regression risk of this diff?” and it answers from the feature map instead of grepping blind.

Deployment modes

The tool API is identical across three deployment modes — only the data path changes. Pick once at the org level; switch any time as your compliance bar shifts.