> ## 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 Cursor over MCP

> Add Keenable to Cursor over MCP with one click, an mcp.json entry or the Keenable CLI, and turn off Cursor's own web search.

*MCP server*

Cursor connects to Keenable as a remote MCP server at `https://api.keenable.ai/mcp`. Add it with a one-click link, an entry in `mcp.json`, or one command with the [Keenable CLI](https://docs.keenable.ai/cli.md). Cursor's agent also has its own Web Search and Web Fetch tools. If both sets of tools are on, the agent picks between them on each lookup. [Turn Cursor's tools off](#turn-off-the-built-in-search) and Keenable handles every search.

## Install

### One click

[Add to Cursor](cursor://anysphere.cursor-deeplink/mcp/install?name=keenable\&config=eyJ1cmwiOiJodHRwczovL2FwaS5rZWVuYWJsZS5haS9tY3AifQ==)

The link opens Cursor and adds the server with no key, so it runs on the shared public tier: 1,000 requests per hour and up to 10 per second per IP (see [Rate limits](https://docs.keenable.ai/rate-limits.md)). To use your own key, add it to `mcp.json` as below, or use the CLI.

### mcp.json

Add the server to `~/.cursor/mcp.json` to use it in every project, or to `.cursor/mcp.json` in a repository to share it with that project only:

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
{
  "mcpServers": {
    "keenable": {
      "url": "https://api.keenable.ai/mcp",
      "headers": {
        "X-API-Key": "keen_<your_key>"
      }
    }
  }
}
```

The key travels in the `X-API-Key` header. Create one in the [console](https://app.keenable.ai/console); see [Authentication](https://docs.keenable.ai/authentication.md). If the file already has an `mcpServers` object, add the `keenable` entry to it rather than adding a second one. Omit the `headers` block to run on the public tier.

Don't put a project-level `.cursor/mcp.json` that holds your key under version control. Keep the key in the global file, or leave the header out of the shared one.

### Keenable CLI

These commands install the CLI, sign you in and add Keenable to Cursor:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
brew install keenableai/tap/keenable-cli
keenable login
keenable configure-mcp --cursor --yes
```

`keenable login` opens a browser device-code flow and stores the credentials locally. `configure-mcp --cursor` then writes the same entry to `~/.cursor/mcp.json`, with the stored key in its `headers` and `"type": "streamable-http"`. It leaves your other servers in the file as they are.

For CI or headless hosts, `keenable login --api-key <KEY>` works too, but the key lands in shell history. On a developer machine, use the browser flow. Run `keenable reset --cursor` to remove the entry. Other install methods are on the [CLI](https://docs.keenable.ai/cli.md#installation) page.

## Turn off the built-in search

Cursor's agent ships Web Search and Web Fetch tools, enabled by default. Open **Cursor Settings → Agents → Context and Tools** and turn both off (the labels and the exact submenu can move between Cursor releases). Keenable's `search_web_pages` and `fetch_page_content` are then the only search and fetch tools the agent has. Keep Web Fetch on if you want Cursor's own page reader for other work.

Those toggles also apply to subagents. If the settings path above doesn't match your build, open a new Agent chat and check the tools list: when Cursor's own Web Search / Web Fetch are gone and the Keenable tools remain, the switch worked. To turn the built-in search back on, switch the toggles on again.

### Tell the agent which tool to use

A rule makes the choice explicit, which helps when you keep Cursor's tools on. Add it under **Customize → Rules** as a user rule to apply it everywhere, or put it in `AGENTS.md` at the root of a repository:

```markdown theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
## Web search

- Use `search_web_pages` for anything that needs the web.
- Follow a search with `fetch_page_content` to read the sources you cite.
```

To make the agent check a library's current docs before it writes code against it, add the rule in [Docs lookup for coding agents](https://docs.keenable.ai/guides/docs-lookup-for-coding-agents.md).

## Verify

Open **Customize** in the sidebar and check that **keenable** is listed and switched on, with both tools. Then start a new Agent chat and ask something that needs the live web. The agent should call `search_web_pages` without being told to.

> [!NOTE]
>
> If the server is listed but the agent never calls it, start a new chat after adding the server or changing the toggles. If it still searches with its own tool, confirm Web Search is off in settings, or check the chat's tools list as described [above](#turn-off-the-built-in-search).

## Keenable SELECT

**Keenable SELECT** is a second Keenable server that answers a question with one SQL query over live web results and returns a table. It has its own Add to Cursor link; see [SELECT](https://docs.keenable.ai/select.md).

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

## Related pages

> [card] [DeepSeek Harness](https://docs.keenable.ai/integrations/deepseek-harness.md)
>
> Keenable web search and page fetch for DeepSeek Harness's built-in web\_search and web\_fetch tools, with any model and no API key.

> [card] [Codex](https://docs.keenable.ai/integrations/codex.md)
>
> Add Keenable to Codex over MCP or the Plugins Directory, and turn off Codex's built-in web search so the agent calls Keenable.

> [card] [Google Antigravity](https://docs.keenable.ai/integrations/antigravity.md)
>
> Install Keenable from the Plugin Marketplace in Antigravity: web search, page fetch and a web lookup skill, with no API key.

> [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.