MCP tools for AI agents

Dynvo ships an MCP server that Cursor, Claude Code, Cline, and Aider call to get precise codebase context — the same data your engineering leaders see, never your raw source. Your agent stops guessing about your code.

What your agent gets

Right files, not folders

Function-level accuracy. The agent pulls the feature map and reads only the symbols that matter, instead of grepping whole directories.

Owners & hotspots

Who owns this code and where the bug-fix churn concentrates — one tool call, not a Slack thread.

Change impact & regression risk

Which features a diff touches, the co-changed-but-missing files, and a low/medium/high risk level — surfaced before the PR.

Live runtime signal

Production errors (Sentry) and usage (PostHog) joined to each feature automatically — your agent sees what's actually breaking.

Set it up

The MCP is a hosted, OAuth-secured server — connect any client through the standard mcp-remote bridge (the first run opens your browser to authorize) and restart. For Cursor that's ~/.cursor/mcp.json:

~/.cursor/mcp.json

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

Deployment modes (Hosted / Local / VPC) are covered on the Getting started page; runtime joins on Integrations.

The 13 tools

All read-only. They read precomputed scan fields — the engine does the work at scan time, the server just serves it. The same 13 names exist in every deployment mode.

list_featuresEvery feature with name, display name, path count, health, and coverage.

find_featureFuzzy-match a single feature by name or alias; returns its paths, flows, health, coverage, impact, and description.

get_feature_filesThe file paths that make up a feature.

get_flow_filesThe file paths that make up one flow inside a feature.

get_repo_summaryRepo-level counts (features, flows, files), top hotspots, average coverage, and the scan timestamp.

get_hotspotsThe highest bug-fix-ratio / churn files or features (limit defaults to 5).

get_feature_ownersOwners and bus factor for a feature.

analyze_change_impactBlast radius for a set of changed files — which features and flows they touch, co-changed-but-missing files, and recommendations. Engine-free path overlap.

get_regression_riskA low / medium / high / critical risk level from bug-fix ratio weighted by path overlap of the touched features.

find_symbols_in_flowPrecise functions and classes per file for a flow, with line ranges and deeplinks (falls back to file paths when symbols are absent).

find_symbols_for_featureThe same symbol-level detail, aggregated across all of a feature's flows.

get_feature_errorsProduction errors mapped to a feature via Sentry (hosted); returns a graceful unavailable result on local MCP.

get_feature_pageviewsPostHog traffic and usage for a feature (hosted); graceful unavailable result on local MCP.

Works with your agents

Any MCP-compatible client — Cursor, Claude Code, Cline, Aider, Continue, and Claude.ai web (hosted mode). Drop the server into the config, restart the agent, and start asking questions that previously needed a senior engineer.

Always fresh

After every push an incremental scan reruns in about 5 seconds for cents in LLM cost, so the agent's context never goes stale — and PR branches get their own current scan, separate from main. Side benefit: 60–80% fewer tokens per query than a naive grep-and-read workflow.