> ## 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

# Get help

> Where to report a problem with Keenable, and what to include so we can find your request.

Email [support@keenable.ai](mailto:support@keenable.ai) for anything about your account, billing or the API. Ask other questions and talk to the Keenable team in the [Keenable Discord](https://discord.gg/be3QybVZ2P). You can also use the [contact form](https://keenable.ai/contact).

## Ask in Discord

The [Keenable Discord](https://discord.gg/be3QybVZ2P) is the place to ask how to use search, fetch, Monitors, the SDKs, the CLI or an integration, and to talk to the Keenable team. Never post an API key there. For a problem with your account or billing, email [support@keenable.ai](mailto:support@keenable.ai) instead.

| Your question | Where to go |
| - | - |
| How to use Keenable, or feedback for the team | [Keenable Discord](https://discord.gg/be3QybVZ2P) |
| Your account, billing or a failing request | [support@keenable.ai](mailto:support@keenable.ai) |
| Whether the API is down | [status.keenable.ai](https://status.keenable.ai) |
| A bug in an SDK or the CLI | [A GitHub issue](#report-a-bug-in-the-sdks-or-the-cli) |

## Check service status

The status page at [status.keenable.ai](https://status.keenable.ai) shows whether the Keenable Search API and Content API are up, with 90 days of uptime history. Check it first when requests fail with `5xx` errors or time out. Fetch runs on the Content API.

## Report a bug in the SDKs or the CLI

Open a GitHub issue in the matching repository:

* SDKs (Python, TypeScript, Go, Rust): [keenableai/keenable-sdk](https://github.com/keenableai/keenable-sdk/issues)
* CLI: [keenableai/keenable-cli](https://github.com/keenableai/keenable-cli/issues)

## What to include

* The `X-Request-Id` header value from the response. Search and fetch responses carry it, and Keenable uses it to find your request in the logs. Error responses carry it too, and repeat it as `request_id` in the body. If you have no response at all, for example after a timeout, include the time of the request instead.
* Your SDK or CLI and its version, for example `keenable 0.1.3` for Python.
* The request, without your API key: the endpoint, the parameters, and the status and body you got back.

Before you write, check [Errors](https://docs.keenable.ai/errors.md) and the [FAQ](https://docs.keenable.ai/faq.md). Most statuses have a fix you can apply right away. To look up a field or term, see the [Glossary](https://docs.keenable.ai/glossary.md).

## Report a problem from an agent

If your agent is connected to the Keenable docs MCP server, it can report a problem with the `submit_feedback` tool. Ask it to include the page, what it expected, what happened, and the `X-Request-Id` value if it has one.


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