> ## 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

# Where Keenable is listed: MCP registries and directories

> Every MCP registry, connector directory and skill catalog that lists Keenable, with a link to each listing and the install command it uses.

Install Keenable from the catalog you already use. Every listing on this page points at Keenable's hosted MCP server or at the `keenable-web-search` skill. The MCP server listings give you the same tools wherever you find them: `search_web_pages` and `fetch_page_content`. The skill listings give your agent search through a Python script, with no MCP client and no page fetch tool. All listings but the OpenAI plugin work with no API key to start. See the [MCP server](https://docs.keenable.ai/mcp-server.md) reference for per-client setup.

## Listings

| Listing | What it lists | How you install from it |
| - | - | - |
| [Claude Connectors Directory](https://docs.keenable.ai/integrations/claude.md) | Keenable Web Search connector | **Customize → Connectors**, then search for **Keenable Web Search**. |
| [OpenAI Plugins Directory](https://docs.keenable.ai/integrations/chatgpt.md) | Keenable plugin for ChatGPT and Codex | **Plugins** in ChatGPT, then search for **Keenable**. |
| [Antigravity Plugin Marketplace](https://docs.keenable.ai/integrations/antigravity.md) | Keenable plugin with search, fetch and the skill | **Customizations → Marketplace → Keenable**. |
| [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers?search=ai.keenable) | Server `ai.keenable/web-search`: the remote endpoint and the `@keenable/mcp` npm package | Clients that read the registry install it by that name. See [Read the registry entry](#read-the-registry-entry). |
| [GitHub MCP Registry](https://github.com/mcp/ai.keenable/web-search) | Server `ai.keenable/web-search` | **Install** on the listing, then pick VS Code. See [VS Code from the GitHub MCP Registry](#vs-code-from-the-github-mcp-registry). |
| [Glama](https://glama.ai/mcp/connectors/ai.keenable.api/keenable-web-search) | Keenable Web Search connector | Add the connector in Glama. It connects to the hosted server. |
| [PulseMCP](https://www.pulsemcp.com/servers/keenable-web-search) | Server `ai.keenable/web-search`, marked official | Copy the remote URL into your client. No account or key. |
| [mcp.so](https://mcp.so/servers/keenable-mcp) | Keenable Web Search | The `npx -y @keenable/mcp` config. See [Local bridge from npm](#local-bridge-from-npm). |
| [LobeHub](https://lobehub.com/mcp/keenableai-keenable-mcp) | Keenable MCP (`keenableai-keenable-mcp`) | The remote URL, or the same npm bridge. |
| [Official MCP servers list](https://github.com/VoltAgent/official-mcp-servers) | Keenable, under Emerging and Independent | Links to the [keenable-mcp repository](https://github.com/keenableai/keenable-mcp). |
| [skills.sh](https://skills.sh/keenableai/keenable-mcp/keenable-web-search) | The `keenable-web-search` agent skill | `npx skills add`. See [Agent skill from skills.sh](#install-the-agent-skill). |
| [ClawHub](https://clawhub.ai/keenable/keenable-web-search) | The `keenable-web-search` agent skill | Install it from ClawHub. The skill has no dependencies. |

If a listing shows a setup that differs from the [MCP server](https://docs.keenable.ai/mcp-server.md) page, follow the MCP server page.

## Read the registry entry

The Official MCP Registry serves each published version of `ai.keenable/web-search` as JSON. To see the latest manifest, with its remote URL and npm package:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=ai.keenable"
```

The entry with `"isLatest": true` is the current one. Its `remotes` list holds a Streamable HTTP endpoint with an optional `X-API-Key` header, and its `packages` list holds `@keenable/mcp` with an optional `KEENABLE_API_KEY` variable.

## VS Code from the GitHub MCP Registry

The GitHub MCP Registry backs one-click MCP installs in VS Code. It reads the same `server.json` as the Official MCP Registry, so **Install** on the listing adds the registry's remote: the keyless endpoint `https://api.keenable.ai/mcp-public?keenable_title=mcp-registry`. That endpoint publishes no OAuth discovery, and it accepts an optional `X-API-Key` header. See [Keyless endpoint for listings and presets](https://docs.keenable.ai/mcp-server.md#keyless-endpoint-for-listings-and-presets).

To write the entry by hand, for example because you will add your own key, point it at `/mcp`:

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

Leave out `headers` to run on the public tier. VS Code uses the top-level key `servers`, not `mcpServers`. Open Copilot Chat in agent mode: the tools picker lists `search_web_pages` and `fetch_page_content`.

## Local bridge from npm

mcp.so, LobeHub and the registry's npm entry use the stdio bridge, which runs locally and forwards to the hosted server. This is the shape for clients that take only local commands, such as Claude Desktop's config file:

```json theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
{
  "mcpServers": {
    "keenable": {
      "command": "npx",
      "args": ["-y", "@keenable/mcp"]
    }
  }
}
```

Add `"env": { "KEENABLE_API_KEY": "keen_<your_key>" }` to the entry to use your key. See [Local bridge (with an API key)](https://docs.keenable.ai/mcp-server.md#local-bridge-with-an-api-key).

## Install the agent skill

The skill gives agents web search through a Python script, with no MCP client. Install it into a project for Claude Code:

```bash theme={"theme":{"light":"github-light-high-contrast","dark":"dark-plus"}}
npx skills add keenableai/keenable-mcp --skill keenable-web-search -a claude-code -y
```

The command prints where it copied the skill. Change `-a` for another agent. See [Agent skill](https://docs.keenable.ai/agent-skill.md).

> [!NOTE]
>
> Most listings start keyless, on the shared public tier at [lower rate limits](https://docs.keenable.ai/rate-limits.md). For the registry entries, Glama, PulseMCP, mcp.so and LobeHub, add an [API key](https://docs.keenable.ai/api-keys.md) in the `X-API-Key` header, or as `KEENABLE_API_KEY` for the npm bridge, to use your organization's limits. The skill takes no key. The Claude connector and the Antigravity plugin take no key either, and their pages show how to add Keenable on your own account. The OpenAI plugin is the exception: you sign in to a Keenable account, and usage counts against that organization's limits and pricing. See [ChatGPT and Codex](https://docs.keenable.ai/integrations/chatgpt.md).

## Related pages

> [card] [Integrations](https://docs.keenable.ai/integrations.md)
>
> Connect Keenable web search to your agent stack: LangChain, LlamaIndex, Haystack, MCP and more.

> [card] [Cursor](https://docs.keenable.ai/integrations/cursor.md)
>
> 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.

> [card] [CLI](https://docs.keenable.ai/cli.md)
>
> Install the Keenable CLI, sign in once, add Keenable to Claude Code, Cursor and Codex over MCP, and search, fetch and run monitors from the terminal.


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