# Pawrly documentation

> Query APIs, files, MCP servers, and databases with SQL — one governed SQL surface for agents and data teams.

This is the documentation index for LLMs. Every link points to the raw Markdown source of a page (the .md endpoints); their internal links also resolve to .md, so you can crawl the docs as Markdown. The human-readable docs live at https://pawrly.dev/docs.

## Start here
- [Overview](https://pawrly.dev/docs/overview.md): What Pawrly is and how the pieces fit together.
- [CLI](https://pawrly.dev/docs/cli.md): Every command: sql, schema, validate, serve, status, mcp-stdio.
- [Configuration](https://pawrly.dev/docs/config.md): The pawrly.yaml schema — sources, secrets, caching, safety.

## Connect data
- [Sources](https://pawrly.dev/docs/sources.md): Wire up APIs, files, databases, warehouses, lakehouses, and MCP servers.

## Model & serve
- [Semantic layer](https://pawrly.dev/docs/semantic.md): Dimensions, measures, relationships, segments, RLS, and pre-aggregations.
- [Materialized tables](https://pawrly.dev/docs/materialize.md): Pin a query, file, or URL as a self-backed table.

## For agents
- [MCP server](https://pawrly.dev/docs/mcp.md): Run Pawrly as an MCP server and consume other MCP servers as sources.

## Operate
- [Observability](https://pawrly.dev/docs/observability.md): Traces, metrics, and a queryable activity log.
- [Architecture](https://pawrly.dev/docs/architecture.md): Engine internals and local vs daemon behavior.
- [Console](https://pawrly.dev/docs/console.md): The web console for browsing sources and running queries.

## More
- [Install guide](https://pawrly.dev/install.md): install + first query, copy-pasteable.
- [Full machine-readable reference](https://pawrly.dev/llms-full.txt): overview, install, sources, features in one fetch.
- [Site index](https://pawrly.dev/llms.txt): the whole site, not just docs.
- [JSON Schema for pawrly.yaml](https://pawrly.dev/pawrly.schema.json): editor completion + validation.