# Connect an AI assistant

> Connect Cursor, Claude, OpenClaw, and other AI assistants to Virlo with the MCP server, plain-text docs files, the ClawHub skill, or the OpenAPI spec.

Source: https://dev.virlo.ai/docs/ai-agents
Markdown: https://dev.virlo.ai/docs/ai-agents.md
Section: For AI assistants

## About the Virlo API (applies to every page)

- Base URL: `https://api.virlo.ai/v1`. Every request needs the header `Authorization: Bearer YOUR_API_KEY` (keys start with `virlo_tkn_`).
- Responses are JSON inside a `data` field, except the `/v1/webhooks` endpoints, which return the object or array directly. Field names are snake_case.
- Prices are in US dollars from a prepaid balance. 1 credit = $0.01. The `X-Cost` response header on each successful response is the exact charge. Errors are free.
- Slow jobs return an ID. Check its status every 15 seconds (or whatever `retry_after_seconds` says) until `finalized` is `true`.
- All docs pages: https://dev.virlo.ai/llms.txt. Every page in one file: https://dev.virlo.ai/llms-full.txt. MCP server for AI assistants: https://dev.virlo.ai/api/mcp/mcp.

---

Let Claude, Cursor, or another AI assistant use Virlo for you.

**At a glance**

- **What it does:** Gives the assistant tools or docs to use Virlo correctly.
- **You send:** An API key from your [dashboard](https://dev.virlo.ai/dashboard/api-keys) and a funded balance.
- **You get back:** An assistant that does research or writes working code.
- **Cost:** Setup is free. Quick data costs $0.05 to $0.25; new research and lookups start at $0.50. Reopening results is free. API responses show each charge in the `X-Cost` header; in chat, check your balance.
- **You choose:** The [MCP server](https://dev.virlo.ai/docs/ai-agents#mcp-configuration) for chat research, the [files](https://dev.virlo.ai/docs/ai-agents#llm-optimized-documentation) or [OpenAPI spec](https://dev.virlo.ai/docs/ai-agents#openapi-specification) for code, or the [OpenClaw skill](https://dev.virlo.ai/docs/ai-agents#openclaw-skill) in OpenClaw.

> **Note:** **No code needed:** use the [MCP server](https://dev.virlo.ai/docs/mcp) inside Claude, or the [Virlo web app](https://app.virlo.ai), a separate product with its own plans.

## MCP server

Add `https://dev.virlo.ai/api/mcp/mcp` as a connector in your AI app for 55 Virlo tools. Claude apps sign you in; others use your API key. [Setup per app](https://dev.virlo.ai/docs/mcp).

## Plain-text files

Paste one into the chat for help writing code. They cover the API, not MCP.

- [`/llms.txt`](https://dev.virlo.ai/llms.txt): a short overview and prices.
- [`/llms-full.txt`](https://dev.virlo.ai/llms-full.txt): every endpoint, parameter, and response field.
- [`/agent-playbook.txt`](https://dev.virlo.ai/agent-playbook.txt): which request answers which question, and how to judge results. Always include it.

## OpenClaw skill

Install [Virlo's skill](https://clawhub.ai/virlo-ai/skills/short-form-market-research-brain) from ClawHub, OpenClaw's skill store. `@virlo-ai` marks the official copy.

**cURL:**

```bash
openclaw skills install @virlo-ai/short-form-market-research-brain
```

Add your key to `~/.openclaw/openclaw.json` as below, or the skill won't appear.

```json5
{
  skills: {
    entries: {
      "short-form-market-research-brain": {
        env: { VIRLO_API_KEY: "YOUR_API_KEY" }
      }
    }
  }
}
```

## OpenAPI spec

For code generators and Postman.

- **Spec file:** [`https://api.virlo.ai/openapi.json`](https://api.virlo.ai/openapi.json)
- **Browse it:** [`https://api.virlo.ai/api`](https://api.virlo.ai/api). Ignore the internal `/admin` routes.

## Tips

- **Ask for your balance first** (free: `GET /v1/account/balance`).
- **Use a [Content Research Agent](https://dev.virlo.ai/docs/agents)** for "what's working in this niche?" Most runs finish within 20 minutes. Ask the assistant to check back, or have code wait for `finalized: true` ([how results load](https://dev.virlo.ai/docs/async-data)).

---

More in For AI assistants:

- [MCP server](https://dev.virlo.ai/docs/mcp.md)
- [Research playbook](https://dev.virlo.ai/docs/agent-playbook.md)