> ## 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

# Obscura browser MCP server with Keenable search

> Add a web_search tool to Obscura's MCP server with OBSCURA_WEB_SEARCH=keenable, so the agent finds pages before it browses them. No key needed.

*Search tool in Obscura's MCP server*

[Obscura](https://github.com/h4ckf0r0day/obscura) is a headless browser with an MCP server, `obscura mcp`. Its browser tools act on pages the agent already has a URL for. Set `OBSCURA_WEB_SEARCH=keenable` and the server also lists a `web_search` tool backed by Keenable, so the agent can find pages first. It works without an API key.

→ [Web search in Obscura's MCP server guide](https://github.com/h4ckf0r0day/obscura/blob/main/docs/Use-the-MCP-server.md#web-search-optional)

## Install

The `web_search` tool ships in Obscura 0.2.7 and later. Download the latest release binary, for example on Linux x86\_64:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl -LO https://github.com/h4ckf0r0day/obscura/releases/latest/download/obscura-x86_64-linux.tar.gz
tar xzf obscura-x86_64-linux.tar.gz
```

Obscura's README lists the archives for other platforms, Scoop on Windows and the source build.

## Turn on web search

Add the variable to the server's environment in your MCP client config. For Claude Desktop, edit `claude_desktop_config.json`:

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
{
  "mcpServers": {
    "obscura": {
      "command": "/path/to/obscura",
      "args": ["mcp"],
      "env": { "OBSCURA_WEB_SEARCH": "keenable" }
    }
  }
}
```

Restart the client. The tool list now has `web_search` next to Obscura's browser tools. In Claude Code, pass the variable with `-e`:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
claude mcp add obscura -e OBSCURA_WEB_SEARCH=keenable -- /path/to/obscura mcp
```

## The web\_search tool

| Argument | Default | What it does |
| - | - | - |
| `query` | required | The search query. |
| `limit` | `5` | Number of results, up to 50. |

The tool returns one JSON object per line, each with `title`, `url` and `snippet`. A response larger than 1 MiB after decompression returns a tool error. Each call goes from Obscura's own HTTP client to `api.keenable.ai`, through the proxy you configured for Obscura.

| Variable | What it does |
| - | - |
| `OBSCURA_WEB_SEARCH=keenable` | Lists the `web_search` tool. Without it, the tool doesn't exist. |
| `KEENABLE_API_KEY` | Optional. With a key, Obscura calls `/v1/search` with `X-API-Key` instead of the keyless `/v1/search/public`. Calls are billed to your organization's [monthly allowance, then its balance](https://docs.keenable.ai/credits.md). |

> [!NOTE]
>
> Without a key, searches run on the shared public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md). Add `KEENABLE_API_KEY` to the server's `env` block to use your organization's limits. See [API keys](https://docs.keenable.ai/api-keys.md).

## Related pages

> [card] [hyperresearch](https://docs.keenable.ai/integrations/hyperresearch.md)
>
> Use Keenable as the web provider in hyperresearch, the deep-research pipeline, for search and page fetch. No key or extra install, 0.13.1 and later.

> [card] [career-ops](https://docs.keenable.ai/integrations/career-ops.md)
>
> Find job postings on employers' own ATS pages from career-ops with the Keenable plugin: a search command and a portals.yml provider. No key needed.

> [card] [Qwen-MM-Plugins](https://docs.keenable.ai/integrations/qwen-mm-plugins.md)
>
> Use Keenable for web\_search and web\_extractor in the Qwen-MM-Plugins search plugin with QWEN\_MM\_SEARCH\_BACKEND=keenable. Works without an API key.

> [card] [Fetch quickstart](https://docs.keenable.ai/products/fetch.md)
>
> Turn any URL into clean markdown your model can read, or get only the part a prompt asks for. Try it with no API key. Code, cost per call and gotchas.


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