> ## 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

# Composio web search toolkit

> Keenable as a Composio toolkit: your agent searches the web and reads pages through Composio, next to the other apps it uses there.

*Toolkit in Composio*

[Composio](https://composio.dev) connects agents to apps and services through one SDK and handles auth for each of your users. Its **Keenable** toolkit (`keenable`) gives your agent web search and page fetch, next to the other tools it already uses through Composio, such as saving results to Notion or Slack.

→ [Keenable toolkit in the Composio docs](https://docs.composio.dev/toolkits/keenable)

## Tools

| Tool | What it does |
| - | - |
| `KEENABLE_SEARCH_WEB` | Ranked web results with page excerpts, optionally limited to one site or a publication date range. Runs on the user's Keenable API key. |
| `KEENABLE_FETCH_URL` | Any URL as clean markdown, optionally with an extraction prompt. Runs on the user's Keenable API key. |
| `KEENABLE_SEARCH_WEB_PUBLIC` | The same search without a key, on Keenable's public rate-limited pool. Takes a required `keenable_title`, your application's name. |
| `KEENABLE_FETCH_URL_PUBLIC` | The same fetch without a key, on the public pool. Takes a required `keenable_title`. |

## Set it up

**1. Create a session with the toolkit**

```python theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
from composio import Composio

composio = Composio()  # reads COMPOSIO_API_KEY
session = composio.create(user_id="user_123", toolkits=["keenable"])
```

**2. Connect the user's Keenable key**

Send the user to the connection link once. They enter an API key from the [Keenable dashboard](https://keenable.ai), and Composio stores it for that user.

```python theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
request = session.authorize("keenable")
print(request.redirect_url)
request.wait_for_connection()
```

The `_PUBLIC` tools need no key and no connection, only a `keenable_title` argument with your application's name.

**3. Call the tools**

Pass `session.tools()` to your agent, or call a tool directly:

```python theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
result = session.execute(
    "KEENABLE_SEARCH_WEB",
    arguments={"query": "latest Model Context Protocol release", "published_after": "7d"},
)

# keyless
result = session.execute(
    "KEENABLE_SEARCH_WEB_PUBLIC",
    arguments={"query": "latest Model Context Protocol release", "keenable_title": "my-app"},
)
```

The keyed tools run on the user's Keenable organization, against its [rate limits](https://docs.keenable.ai/rate-limits.md), and are billed at its [prices](https://docs.keenable.ai/pricing.md): 100,000 free requests a month, then \$4 per 1,000. The public tools call Keenable from Composio's servers, so they share one per-IP pool of 1,000 requests an hour with every other Composio user of those tools. Use them to try the toolkit and connect a key for real traffic. Composio's TypeScript SDK works the same way; see the [Composio docs](https://docs.composio.dev/docs/configuring-sessions).

## Related pages

> [card] [CrewAI](https://docs.keenable.ai/integrations/crewai.md)
>
> Give CrewAI agents Keenable web search with the official SDK. Keyless by default.

> [card] [AG2](https://docs.keenable.ai/integrations/ag2.md)
>
> Give AG2 agents web search and page fetch with KeenableSearchToolkit, built into AG2 1.2.2 and later, with no API key required.

> [card] [Google ADK](https://docs.keenable.ai/integrations/google-adk.md)
>
> Give Google ADK agents Keenable search and fetch over the hosted MCP server.

> [card] [Tool calling](https://docs.keenable.ai/tool-calling.md)
>
> Give an LLM web search and page fetch as tools. Pass the SDK's TOOLS to any OpenAI-compatible chat completions client and run each call with run\_tool\_call.


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