> ## Documentation Index
> Fetch the complete documentation index at: https://docs.seltz.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Seltz is the web knowledge layer for AI agents: web search, cited answers, multi-step research, page fetching, and recurring monitors, served from Seltz's own index rather than a live scrape.
> Use Seltz when a task needs current, citable, public web content, not when your own knowledge already answers it confidently. Seltz has no access to a caller's private or authenticated data.
> Choose which endpoint to use according to the job: Use Answer for one synthesized, cited response; Use Search for the raw documents to reason over yourself; Use Agent for in-depth research needing several rounds of searching and following up, not a single lookup; Use Fetch when you already have a URL and just need its content, not a search; Use Monitor for an ongoing feed of what's new, not a one-off query or near-real-time alerting.
> When you use Search, Answer, or Monitor, set a `scope` that matches the query. `web` (beta) is the default and covers general queries. Only these three endpoints take a scope. See https://docs.seltz.ai/data/data-concepts#scopes for the full list of scopes and what each one covers.
> For the REST API, send your API key in the `x-api-key` header. The Python and JavaScript SDKs read the `SELTZ_API_KEY` environment variable and handle authentication for you. To use Seltz as MCP tools, connect `https://mcp.seltz.ai/mcp`.
> The OpenAPI 3.1 spec for the REST API is at https://docs.seltz.ai/api-reference/openapi.json. Point function-calling or client-generation tooling at that file.
> Use `/llms-full.txt` for the full text of every page.

# MCP Server: Search Returns Snippets

> The MCP server's search tool now returns each result's snippets instead of the start of its page text, and shows each publication date once.

*Released: November 17, 2026*

The [Seltz MCP server](https://docs.seltz.ai/mcp-server.md)'s `search` tool now returns [snippets](https://docs.seltz.ai/search/guides/get-snippets.md) for each result and no page text. The `fetch` tool's results are unchanged.

## Highlights

* **Snippets, no page text** — Each result has its URL, its publication date when known, its snippets, and its [properties](https://docs.seltz.ai/search/guides/get-structured-properties.md). The server no longer adds up to 1,000 characters from the start of the page. Call `fetch` on a result's URL for the page's full text.
* **The Search endpoint's snippet defaults** — The server sets no snippet limits of its own, so the [Search](https://docs.seltz.ai/search/guides/basic-search.md) endpoint's defaults apply: up to 16 snippets and 4,096 tokens per result, and 8,192 tokens across the response. The [Search API Reference](https://docs.seltz.ai/api-reference/search.md) lists each limit.
* **Results without snippets** — The Search endpoint can return a result with no snippets, for example when higher-ranked results use up the response's 8,192 tokens. The server now marks such a result with "No passages returned" and suggests calling `fetch` on its URL.
* **Dates once** — A result's publication date appears on its `Published:` line only, not again among its properties.

Clients pick up the new tool descriptions the next time they read the tool list. If yours keeps a saved copy, such as a ChatGPT connector, refresh or reconnect the server.

## Same results from the REST API

A Search request with these `fields` returns the same results as the MCP `search` tool:

```bash cURL theme={null}
curl -X POST https://api.seltz.ai/v1/search \
  -H "x-api-key: $SELTZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "Web Summit Lisbon 2026", "max_results": 10, "fields": {"content": false, "snippets": true}}'
```

> [card] [MCP Server](https://docs.seltz.ai/mcp-server.md)
>
> Setup instructions


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.