> ## 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 Gemini and Gemini CLI

> Add Keenable to the Gemini app and Gemini CLI, and keep Gemini CLI's own web search from competing with it.

*MCP custom app*

Give Gemini web search and page reading through Keenable. In the Gemini app, you add Keenable as a custom app by pasting its MCP server URL and signing in to your Keenable account. In Gemini CLI, you add the same server with one command. Gemini also searches the web with Google. In Gemini CLI you can turn that search off. In the Gemini app, you pick Keenable for a prompt with `@`.

## Gemini app

### Add the custom app

You add the app once in the web app at [gemini.google.com](https://gemini.google.com). After that, it works in both the Gemini web app and the Gemini mobile app.

**1. Open Connected Apps**

On your computer, open [gemini.google.com](https://gemini.google.com), click **Settings** at the bottom, then **Connected Apps**. If you don't see **Connected Apps**, click **Personal Intelligence** first, then **Connected Apps**.

**2. Add the server URL**

Under **Custom apps**, click **Add a custom app**, enter this URL, and click **Next**:

```text theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
https://api.keenable.ai/mcp-oauth
```

Leave **Advanced features** as it is. Keenable supports Dynamic Client Registration, so Gemini registers itself and there are no credentials to enter.

**3. Sign in**

Follow the on-screen instructions, sign in to Keenable, and allow access.

Searches then count against your current organization in Keenable, with its [rate limits](https://docs.keenable.ai/rate-limits.md) and [pricing](https://docs.keenable.ai/pricing.md). Signing in also adds the [Monitors tools](https://docs.keenable.ai/mcp-server.md#monitors-tools).

> [!NOTE]
>
> Google limits custom apps to personal Google Accounts, so you can't add one if you sign in to Gemini with a work or school account. You also need to be 18 or over, be in the US, and have Gemini's **History** setting on. See Google's [Connect & manage custom apps](https://support.google.com/gemini/answer/17209137) for the current requirements.

### Use it in a chat

If a connected app fits the prompt, Gemini can call it on its own, but Gemini also searches with Google. Google documents no setting that turns that search off in the Gemini app. To make sure Gemini uses Keenable for a prompt, type `@` in the message box and select the Keenable app.

To turn Keenable off, open **Settings → Connected Apps** again and switch it off under **Custom apps**. To remove it, click **More details → Remove app**, which also unlinks Keenable from your Google Account.

## Gemini CLI

### Add the server

Run this command with your own key in place of `keen_<your_key>`:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
gemini mcp add --transport http --scope user keenable https://api.keenable.ai/mcp \
  --header "X-API-Key: keen_<your_key>"
```

`--scope user` makes it available in every project. Without it, Gemini CLI adds the server to the current project only. The key also adds the [Monitors tools](https://docs.keenable.ai/mcp-server.md#monitors-tools). Omit the `--header` flag to run on the public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md), with the two web tools only.

### Turn off the built-in search

Gemini CLI ships its own `google_web_search` and `web_fetch` tools. Deny them with a policy file. Create `~/.gemini/policies/keenable.toml`:

```toml theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
[[rule]]
toolName = ["google_web_search", "web_fetch"]
decision = "deny"
priority = 100
```

Gemini CLI loads every `.toml` file in `~/.gemini/policies`. A deny rule that names a whole tool removes it from the model's context, so Keenable's `search_web_pages` and `fetch_page_content` are the only search and fetch tools it has left. Drop `"web_fetch"` if you want to keep Gemini's own page reader.

To turn the built-in search back on, delete the file.

### Verify

Run `/mcp` in Gemini CLI to confirm **keenable** is connected with `search_web_pages` and `fetch_page_content` listed, or run `gemini mcp list` from your shell. Then ask a question that needs the live web. Gemini should call `search_web_pages` without being told to.

## What to ask

Keenable gives Gemini two web tools, and Gemini combines them across a longer task.

> [card] Search
>
> Ranked results with an excerpt of each page's text, narrowed to one site or a date range when the question calls for it.

> [card] Read
>
> Any URL as clean markdown: documentation, changelogs, issues, papers, pricing pages.

> [card] Research
>
> Several searches, the pages worth reading, and an answer that cites them.

Ask for the result you want, and say which sources count. In the Gemini app, start with `@` and the Keenable app:

```text theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
What changed in the EU AI Act guidance this month? Use the official
pages and cite each one.
```

```text theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
Find the release notes for every version of zod between the one in package.json
and the latest, list the breaking changes, and update our schemas to match.
```

The first suits the Gemini app. The second suits Gemini CLI, where Gemini can act on what it finds in your repository.

## More from Keenable

Gemini CLI also installs Keenable as an extension, with a skill for web lookups. See [Google Antigravity](https://docs.keenable.ai/integrations/antigravity.md#gemini-cli).

→ [Full MCP server reference](https://docs.keenable.ai/mcp-server.md)

## Related pages

> [card] [CowAgent](https://docs.keenable.ai/integrations/cowagent.md)
>
> Keenable is a built-in web search provider in CowAgent that can run without an API key.

> [card] [Claude](https://docs.keenable.ai/integrations/claude.md)
>
> Add Keenable to Claude and Claude Code, and keep Claude's own web search from competing with it.

> [card] [LibreChat](https://docs.keenable.ai/integrations/librechat.md)
>
> Keenable is the keyless search provider and content scraper built into LibreChat's web search.

> [card] [Agent skill](https://docs.keenable.ai/agent-skill.md)
>
> Install the keenable-web-search agent skill with npx skills add. Your agent searches the web with a bundled script, with no API key and no MCP client.


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