> ## 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 Devin Desktop over MCP

> Add Keenable to Devin Desktop (formerly Windsurf) over MCP. Config paths for Devin Local and the legacy Windsurf data directory.

*MCP server*

Give [Devin Desktop](https://devin.ai/), Cognition's editor formerly called Windsurf, web search and page fetch through the Keenable MCP server at `https://api.keenable.ai/mcp`. Add the server in an `mcp_config.json` file, or with one command from the [Keenable CLI](https://docs.keenable.ai/cli.md).

## Install

### mcp\_config.json

Devin Local reads MCP servers from these files. Use the user-scope file to make Keenable available in every project:

| Scope | Path |
| - | - |
| User | `~/.config/devin/mcp_config.json` (Windows: `%APPDATA%\devin\mcp_config.json`) |
| Project | `.devin/mcp_config.json` |
| Local (gitignored) | `.devin/mcp_config.local.json` |

Add this entry to one of them:

```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>"
      }
    }
  }
}
```

Devin Local reads the address from `url`. Create a key in the [console](https://app.keenable.ai/console?utm_source=docs\&utm_medium=cta\&utm_campaign=devin_desktop\&utm_content=console), and see [Authentication](https://docs.keenable.ai/authentication.md) for details. To run on the public tier, omit the `headers` block and point `url` at the keyless endpoint, `https://api.keenable.ai/mcp-public`. The public tier allows 1,000 requests per hour and up to 10 per second per IP address (see [Rate limits](https://docs.keenable.ai/rate-limits.md)).

Don't commit a config file that holds your key. Put the key in `.devin/mcp_config.local.json` or the user-scope file.

### Legacy Windsurf path

A pre-rebrand install reads `~/.codeium/windsurf/mcp_config.json` instead. Use the same JSON there, with the key `serverUrl` in place of `url`.

### Keenable CLI

Install the CLI, sign in, and write the entry to the user-scope file:

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

`keenable login` opens a browser device-code sign-in and stores your credentials locally. `configure-mcp --devin` writes the entry, with `url` and the stored key, to `~/.config/devin/mcp_config.json`. The command does nothing unless the `~/.config/devin` directory exists. To remove the entry, run `keenable reset --devin`. For other ways to install the CLI, see [CLI](https://docs.keenable.ai/cli.md#installation).

For a pre-rebrand install, `configure-mcp --windsurf` writes the entry with `serverUrl` to the legacy `~/.codeium/windsurf/mcp_config.json` instead.

## Use it

Ask Devin Desktop a question that needs the web, for example "What are the fastest inference providers in 2026? Cite your sources." It calls `search_web_pages` and answers with linked sources. For a known URL, ask it to read the page with `fetch_page_content`.

See [MCP server](https://docs.keenable.ai/mcp-server.md) for the tool list and every other client.

## Related pages

> [card] [oh-my-pi](https://docs.keenable.ai/integrations/oh-my-pi.md)
>
> Use Keenable as the web search engine in oh-my-pi (omp), the coding agent, with the web/keenable model role. Works without an API key.

> [card] [Pi](https://docs.keenable.ai/integrations/pi.md)
>
> Give the Pi coding agent web search and page fetch with the @keenable/pi-search package, or pick Keenable in pi-web-access.

> [card] [OpenClaude](https://docs.keenable.ai/integrations/openclaude.md)
>
> Make Keenable the web search backend in OpenClaude with /search keenable or WEB\_SEARCH\_PROVIDER=keenable. No key needed, in OpenClaude 0.34.0 and later.

> [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.