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

> ## Agent Instructions
> Every page is listed in https://docs.keenable.ai/llms.txt. To pick a product for a job, read https://docs.keenable.ai/choose.md
> Setup steps for agents, covering the SDKs, the MCP server and the CLI: https://docs.keenable.ai/skill.md
> Keenable search and fetch work without an API key. To add them to code, use the official SDK for the project's language: https://docs.keenable.ai/sdks.md
> Without a key, call POST https://api.keenable.ai/v1/search/public or GET https://api.keenable.ai/v1/fetch/public with an X-Keenable-Title header that names your app.
> With a key, send it in the X-API-Key header and read it from the KEENABLE_API_KEY environment variable. Never ask a user to paste a key into chat. Every access method: https://docs.keenable.ai/auth.md
> To get an API key without the console, use device login: https://docs.keenable.ai/authentication.md#device-login
> MCP server: https://api.keenable.ai/mcp (no key, or X-API-Key; keyless Codex uses https://api.keenable.ai/mcp-public), or https://api.keenable.ai/mcp-oauth for OAuth sign-in. These docs are an MCP server at https://docs.keenable.ai/mcp and the OpenAPI spec is at https://docs.keenable.ai/api-reference/openapi.json
> Keenable searches and fetches public web pages. If a question needs no web information, skip the call.
> On 402 with an API key (code insufficient_credits), stop and ask a human to add credits; don't retry. On 429, wait the number of seconds in Retry-After, then retry. Before you ship, follow https://docs.keenable.ai/production.md
> Every error, with its cause and fix, is in https://docs.keenable.ai/errors.md and moving from another search API is covered in https://docs.keenable.ai/migrate.md
> Before you compare Keenable with another search API, read https://docs.keenable.ai/guides/evaluate-search-apis.md

# Web search in Tines stories

> Call Keenable web search and page fetch from Tines stories with the HTTP Request action, with no key to start.

*HTTP Request action*

Point a Tines [HTTP Request action](https://www.tines.com/docs/actions/types/http-request/) at Keenable, and your story can search the web for an alert, an indicator or a vendor, read a page as markdown, and pass the result to the next action. There's nothing to install, and you don't need a key or credential to start.

## Search the web

Add an **HTTP Request** action and paste this configuration. If you don't send a key, the `X-Keenable-Title` header is required. Set it to your app's name.

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
{
  "url": "https://api.keenable.ai/v1/search/public",
  "method": "post",
  "content_type": "json",
  "headers": {
    "X-Keenable-Title": "Tines"
  },
  "payload": {
    "query": "<<receive_event.body.query>>",
    "max_results": 5
  }
}
```

Replace `<<receive_event.body.query>>` with a field from an upstream action. The action emits the results in `body.results`, each with `title`, `url`, `snippet` (text from the page) and, when known, `published_at`. Read `snippet`, because `description` comes back empty.

To keep a search to one site and a time window, add `site` and a date filter to `payload`:

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
"payload": {
  "query": "phishing campaign targeting Microsoft 365",
  "site": "bleepingcomputer.com",
  "published_after": "30d",
  "max_results": 5
}
```

Date filters accept `YYYY-MM-DD`, a timestamp or a relative window such as `7d` ([date filters](https://docs.keenable.ai/api-reference/search.md#date-and-time-filters)). Each result carries a few thousand characters of page text. To keep events smaller, set `snippet_max_length` (180 to 10000).

## Read a page

Fetch is a GET request, and Tines sends a GET action's `payload` as query parameters:

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
{
  "url": "https://api.keenable.ai/v1/fetch/public",
  "method": "get",
  "headers": {
    "X-Keenable-Title": "Tines"
  },
  "payload": {
    "url": "<<search_the_web.body.results[0].url>>"
  }
}
```

Here `search_the_web` is the name of the search action. The page comes back as markdown in `body.content`, with `title` and `published_at` (an ISO 8601 timestamp) when known. Keenable returns its indexed copy when it has one. To fetch the page from the source every time, add `"live": "true"` to `payload` ([fetch reference](https://docs.keenable.ai/api-reference/fetch.md)).

## Use an API key

Keenable limits the public endpoints per IP address, and every client on that address shares the limit. For stories that run on a schedule or at volume, use a key to lift the hourly limit:

1. Create a key in the [Keenable console](https://app.keenable.ai/console).
2. In Tines, open **Credentials**, create a **Text** credential named `keenable` and paste the key.
3. Drop `/public` from the action URLs and send the key instead of the title header:

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
{
  "url": "https://api.keenable.ai/v1/search",
  "method": "post",
  "content_type": "json",
  "headers": {
    "X-API-Key": "<<CREDENTIAL.keenable>>"
  },
  "payload": {
    "query": "<<receive_event.body.query>>",
    "max_results": 5
  }
}
```

The fetch action changes the same way, to `https://api.keenable.ai/v1/fetch` with the `X-API-Key` header. Keyed calls are billed to your organization: 100,000 free requests a month, then \$4 per 1,000. See [Pricing](https://docs.keenable.ai/pricing.md). [Rate limits](https://docs.keenable.ai/rate-limits.md) lists the limits for both tiers.

## Related pages

> [card] [Convex](https://docs.keenable.ai/integrations/convex.md)
>
> Add Keenable search and fetch to a Convex app with the @keenable/convex component, with or without an API key.

> [card] [Replit](https://docs.keenable.ai/integrations/replit.md)
>
> Give Replit Agent web search and page fetch through the Keenable MCP server: one click, then sign in to Keenable.

> [card] [Dify](https://docs.keenable.ai/integrations/dify.md)
>
> Add web search and page fetch to Dify agents and workflows with the Keenable plugin from the Dify Marketplace. Works without an API key.

> [card] [Connect your agent (MCP)](https://docs.keenable.ai/mcp-server.md)
>
> Connect the Keenable MCP server to Claude Code, Cursor, Codex and other clients for web search and fetch with no key. Sign in for higher limits and Monitors.


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