> ## 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 for Replit Agent over MCP

> Give Replit Agent web search and page fetch through the Keenable MCP server: one click, then sign in to Keenable.

*MCP server*

Add Keenable to Replit once, and Replit Agent can search the web and read pages in every app and chat on your Replit account. `search_web_pages` returns live results with site and date filters, and `fetch_page_content` returns a page as clean markdown.

## Add Keenable

[Add to Replit](https://replit.com/integrations?mcp=eyJkaXNwbGF5TmFtZSI6IktlZW5hYmxlIiwiYmFzZVVybCI6Imh0dHBzOi8vYXBpLmtlZW5hYmxlLmFpL21jcC1vYXV0aCJ9)

**1. Open the install link**

Click **Add to Replit**. Replit opens its Integrations page with the Keenable server filled in.

**2. Sign in to Keenable**

Click **Test & save**, then sign in to Keenable and allow access. Replit discovers Keenable's sign-in page, so you don't paste a key.

**3. Ask Agent to use it**

Keenable now appears under **MCP Servers** with its status, and Agent loads its tools in every project. To make Agent use Keenable, name it in your request:

> Use Keenable to find this week's releases of the libraries this app depends on and list what changed.

Searches 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): 100,000 free requests a month, then \$4 per 1,000.

To add the server by hand, open [replit.com/integrations](https://replit.com/integrations) and scroll to **MCP Servers for Replit Agent**. Click **+ Add MCP server**, name it **Keenable**, enter this URL and click **Test & save**:

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

### With an API key

To use a key instead of signing in, add `https://api.keenable.ai/mcp`, open **Advanced settings**, and add the header `X-API-Key` with your key (`keen_<your_key>`, from the [console](https://app.keenable.ai/console)).

> [!NOTE]
>
> If you add `https://api.keenable.ai/mcp` with no key, it runs on the shared public tier. Replit Agent calls MCP servers from Replit's cloud, so it shares that tier's per-IP hourly limit with other Replit traffic, and the limit can run out in the middle of a task. Sign in or use a key for anything past a first try.

## Search inside the app you build

To give the app itself web search for its users, have Agent call Keenable from the app's backend with the SDK (`npm install keenable` or `pip install keenable`). The MCP server above only gives Agent a tool for its own work.

Put your key in the app's **Secrets** as `KEENABLE_API_KEY` first. A published app serves all its users from one server, so without a key they would all share one per-IP hourly limit.

> Add web search to this app with the Keenable SDK (the `keenable` package). Call it from the server, read the key from the `KEENABLE_API_KEY` secret, and show each result's title, URL and snippet.

Endpoints and parameters are in the [API reference](https://docs.keenable.ai/api-reference.md).

## Related pages

> [card] [Tines](https://docs.keenable.ai/integrations/tines.md)
>
> Call Keenable web search and page fetch from Tines stories with the HTTP Request action, with no key to start.

> [card] [RAGFlow](https://docs.keenable.ai/integrations/ragflow.md)
>
> Give RAGFlow agents web search with the Keenable tool built into RAGFlow's visual agent builder. Works without an API key.

> [card] [Convex](https://docs.keenable.ai/integrations/convex.md)
>
> Add Keenable search and fetch to a Convex app with the @keenable/convex component, with or without an API key.

> [card] [Connect your agent (MCP)](https://docs.keenable.ai/mcp-server.md)
>
> Connect the Keenable MCP server to Claude Code, Cursor, Codex and other clients for web search and fetch with no key. Sign in for higher limits and Monitors.


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