> ## 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

# Keenable cookbook: recipes and guides for web search

> Recipes and guides for building on Keenable. Search by topic, filter by product, and open a runnable example for search, fetch, monitors and SELECT.

Runnable examples for building on Keenable. A recipe builds one complete app, from the first call to the production notes. A guide solves one task, such as filtering by date or capping page size. Every entry has code in several languages and a real response. Most run with no API key.

| Entry | Type | What you get | Products |
| - | - | - | - |
| [RAG with fresh web results](https://docs.keenable.ai/recipes/rag-with-fresh-web-results.md) | Recipe | Retrieve pages published in the last 30 days, render them as numbered sources and prompt your model to answer with citations. Runs with no API key. | Search |
| [Research loop](https://docs.keenable.ai/recipes/research-loop.md) | Recipe | Research a broad question with search and fetch: run focused searches at once, merge results without duplicate URLs, read the top pages with a size cap. | Search, Fetch |
| [Fact-check with citations](https://docs.keenable.ai/recipes/fact-check-with-citations.md) | Recipe | Check a claim against the pages that discuss it: search, then fetch each page with a prompt that returns a verdict and the quoted sentence, per URL. | Search, Fetch |
| [News monitor to Slack](https://docs.keenable.ai/recipes/news-monitor-to-slack.md) | Recipe | Post each new page a Keenable monitor finds to Slack: verify the monitor.result.found webhook, then forward the title, link and summary to an incoming webhook. | Monitors |
| [Competitor watch](https://docs.keenable.ai/recipes/competitor-watch.md) | Recipe | Watch a competitor's own domains with a Keenable monitor and get a weekday 9:00 digest of new pages, summarized in your own JSON Schema. | Monitors |
| [Enrich a list with SELECT](https://docs.keenable.ai/recipes/enrich-a-list-with-select.md) | Recipe | Add web facts to every item in a list with one SELECT query: one search per item, fields extracted by an LLM, one row per item with its source count. | SELECT |
| [Agent pays with x402](https://docs.keenable.ai/recipes/agent-pays-with-x402.md) | Recipe | Give an agent web search and fetch with no account or API key: it pays each call in USDC on Base over x402, and your client refuses offers above a cap. | Search, Fetch, Pay per request |
| [Search, then fetch](https://docs.keenable.ai/guides/search-then-fetch.md) | Guide | How to answer from search snippets first, fetch a page only when a snippet falls short, ask fetch for only the part you need, and when to set live=true. | Search, Fetch |
| [Ground answers with citations](https://docs.keenable.ai/guides/ground-answers-with-citations.md) | Guide | How to turn search results into a numbered source block with to\_context(), ask the model to cite \[n], and map citations back to URLs with cited(). | Search |
| [Docs lookup for coding agents](https://docs.keenable.ai/guides/docs-lookup-for-coding-agents.md) | Guide | How to give a coding agent current library docs and changelogs: connect the MCP server, add an AGENTS.md rule, search one docs site, fetch with a prompt. | Search, Fetch |
| [Filter by date](https://docs.keenable.ai/guides/filter-by-date) | Guide | How to keep search results inside a date window with published\_after and published\_before, relative offsets such as 7d, and the acquired filters. | Search |
| [Filter by domain](https://docs.keenable.ai/guides/filter-by-domain.md) | Guide | How to search one site with site, leave hosts out with exclude\_domains, and combine both, with the entry rules and the 400 invalid\_filter fix. | Search |
| [Search operators](https://docs.keenable.ai/guides/search-operators.md) | Guide | How to put quoted phrases, site:, OR, - and parentheses in a query, when to use them instead of the site and exclude\_domains parameters, and the 400 fix. | Search |
| [Choose a search mode](https://docs.keenable.ai/guides/choose-a-search-mode.md) | Guide | How to pick pro for deeper retrieval or realtime for the fastest response, set the mode in each client, and check which mode served a call. | Search |
| [Result size](https://docs.keenable.ai/guides/result-size.md) | Guide | How to set max\_results (1 to 50) and snippet\_max\_length (180 to 10,000) so search results fit your context, and when to send disable\_cards for web pages only. | Search |
| [Fetch with a prompt](https://docs.keenable.ai/guides/fetch-with-prompt.md) | Guide | How to pass a prompt to fetch so content holds only the facts you asked for, write prompts that return parseable output, and handle the 2,000-character limit. | Fetch |
| [Live fetch](https://docs.keenable.ai/guides/live-fetch.md) | Guide | How to set live=true so fetch reads a page from its source instead of the indexed copy, when that's worth it, and how a live read is billed as fetch.live. | Fetch |
| [Long pages](https://docs.keenable.ai/guides/long-pages.md) | Guide | How to cap fetch output with max\_chars, read truncated and total\_chars to see what was cut, and switch to a prompt when a page runs past 50,000 characters. | Fetch |
| [Create a monitor](https://docs.keenable.ai/guides/create-a-monitor.md) | Guide | How to create a Keenable monitor: write the topic, limit it to the sites you trust, set a cron schedule, tag it with metadata and retry safely. | Monitors |
| [Read monitor results](https://docs.keenable.ai/guides/read-monitor-results.md) | Guide | How to read the pages a Keenable monitor found: poll new results since your last read, read each run's digest, or let your agent read them over MCP. | Monitors |
| [Monitor webhooks](https://docs.keenable.ai/guides/monitor-webhooks.md) | Guide | Get each new monitor result at your endpoint: subscribe to monitor.result.found, verify the Standard Webhooks signature, test locally, debug failed deliveries. | Monitors |
| [Keyless access](https://docs.keenable.ai/guides/keyless-access.md) | Guide | How to call search and fetch with no API key: the /public paths, the X-Keenable-Title header, /mcp-public, and the 1,000 per hour keyless limit per IP. | Search, Fetch |
| [High-volume research](https://docs.keenable.ai/guides/high-volume-research.md) | Guide | How to run many searches and fetches in parallel: cap calls in flight, retry a 429 after Retry-After, group a run with a session ID, and raise your limit. | Search, Fetch |
| [Cost at volume](https://docs.keenable.ai/guides/cost-at-volume.md) | Guide | How to estimate a monthly Keenable bill: add searches and fetches, subtract 100,000 free requests, multiply by \$4 per 1,000, then check it with usage.credits. | Search, Fetch |
| [Evaluate search APIs](https://docs.keenable.ai/guides/evaluate-search-apis.md) | Guide | Compare web search APIs fairly: build a gold set, run the same queries with equal settings, judge results blind and avoid the pitfalls that skew scores. | Search |

## Build with your coding agent

Every recipe starts with a **Recipe prompt** that points your coding agent at the Markdown version of the page, so the agent reads the same steps and limits you do. Paste it into Claude Code, Cursor, Codex or any agent that can read a URL. The [recipes overview](https://docs.keenable.ai/recipes.md) explains which recipes need an API key.

## Related pages

* [Recipes](https://docs.keenable.ai/recipes.md): the complete apps, with when each one runs.
* [All guides](https://docs.keenable.ai/guides.md): how-to guides for search and fetch, with the parameters each covers.
* [Best practices](https://docs.keenable.ai/best-practices.md): query writing, parallel searches and context size.


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