# Galon Search > Turn a web page into Markdown, HTML or links, map the links of a site, or crawl a few pages, through one API key, with robots rules honoured. Server side only: read the key from the `GALON_API_KEY` environment variable. Call `GET https://api.galon.ai/v1/tools` first: use only what it lists for this key. Send an `Idempotency-Key` with every write and reuse it on retry. On an error, act on `detail.code` and follow `detail.next_action`. ## What it does - Scrape a URL into Markdown, HTML, raw HTML or its links. - Map a site: list the links it exposes. - Crawl a bounded set of pages from a starting URL, as an asynchronous job you can follow or cancel. - robots.txt is honoured and each host is fetched politely, one request a second. - Crawl results are kept for 24 hours. ## API - `POST /v1/search/v2/scrape`: Read a web page - `POST /v1/search/v2/map`: List a site's links - `POST /v1/search/v2/crawl`: Read a whole site - `GET /v1/search/v2/crawl/{crawl_id}`: Read a crawl job - `DELETE /v1/search/v2/crawl/{crawl_id}`: Stop a crawl job - `GET /v1/search/v2/crawl/{crawl_id}/errors`: Read a crawl job's refusals - `GET /v1/search/indexes`: List search indexes - `POST /v1/search/indexes`: Create a search index - `GET /v1/search/indexes/{name}`: Read a search index - `DELETE /v1/search/indexes/{name}`: Delete a search index - `POST /v1/search/indexes/{name}/documents`: Add or update documents - `POST /v1/search/indexes/{name}/query`: Search an index - `GET /v1/search/indexes/{name}/documents/{document_id}`: Read a document - `POST /v1/search/indexes/{name}/documents/delete`: Delete documents - `GET /v1/search/tasks/{task_id}`: Read a search task ## MCP tools Server: `https://api.galon.ai/v1/mcp` (Streamable HTTP). - `search_list_indexes`: List the search indexes of this project. - `search_create_index`: Create a search index from typed fields, or from a first batch of documents (schema inferred). - `search_get_index`: Read an index: schema and document count. - `search_add_documents`: Add or replace up to 1,000 documents in an index, all or nothing. - `search_query`: Full-text search with filters, sorting, facets, pagination and highlights. - `search_get_document`: Read one document of an index by its id. - `search_delete_documents`: Delete up to 1,000 documents of an index by id. - `search_get_task`: Read the result of a document batch. - `search_delete_index`: Delete an index and all its documents. - `search_scrape_page`: Read one public web page as clean Markdown. - `search_map_site`: List the addresses of a site's pages, without reading them. - `search_start_crawl`: Start a background reading of a site's pages, page after page. - `search_get_crawl`: Read the status and the pages of a site reading. - `search_get_crawl_errors`: List the pages a site reading could not read. - `search_cancel_crawl`: Stop a site reading that is still running. ## Docs - [Galon Search guide](/cloud/docs/services/search) - [OpenAPI 3.1 contract](/cloud/docs/openapi.json): the source of truth for routes and fields - [Complete LLM integration guide](/llms-full.txt)