Provides web search capabilities using DuckDuckGo as the backend, returning Exa-compatible search results with optional text and highlights.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
cauce.fyi — the public instance · docs at docs.cauce.fyi
Related MCP server: Local Research MCP Server
mise use -g github:espetro/cauce
cauce serve # UI + API + MCP on http://127.0.0.1:4479Or grab a release binary / build from source: docs/install.md
One web UI, one HTTP API, one MCP server — all reading the same TTL cache.
Tail-tolerant fan-out over pluggable engines (declarative YAML, exec, replay) with hedging and circuit breakers.
Grounded AI answers at POST /api/answer, with optional BYOK and a free daily-answer budget for public instances.
Local archive + search history in SQLite FTS5.
Self-hosted and local-first: a single Rust binary, loopback by default; a public-instance mode exists for the edge.
Path | What it owns |
| Search pipeline, |
| axum HTTP/SSE/MCP, embedded Svelte SPA at |
| Declarative / exec / replay engine runtimes |
| rusqlite |
| Grounded-answer agent loop |
|
|
| YAML engine specs + fixtures |
| exec-protocol SDK + |
End-user docs: docs.cauce.fyi · developer docs: .agents/docs/
Filing a bug? GET /api/report or cauce report produces a redacted JSON bundle to attach — see docs/reporting.md.
This server cannot be deployed
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
Agent-native search engine with live web research optimized for AI agents.
Web search and page reading for AI agents, including JSON APIs, RSS feeds and YouTube.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
