---
title: "Flowise · Scrape.ly Docs"
description: "Add Scrape.ly tools to Flowise agents through the MCP server."
url: https://scrape.ly/docs/flowise
markdown: https://scrape.ly/docs/flowise.md
---

# Flowise

> Add Scrape.ly tools to Flowise agents through the MCP server.

Add Scrape.ly tools to a Flowise agent: it can search the Store, run Actors, wait for their runs, and read the results. Flowise connects to the hosted [MCP server](https://scrape.ly/docs/mcp.md) with its **Custom MCP** tool, so there is nothing to install beyond Flowise.

Create an API token in the [dashboard](https://my.scrape.ly) under **Settings → API & Integrations**. The agent can do anything the token can, including starting paid runs, so give it a scoped key: `actors:run`, `runs:read`, and `datasets:read`, with a **Max charge per day**. See [API keys & permissions](https://scrape.ly/docs/api-keys.md).

## Add the MCP server

1. In Flowise, open **Variables** and add a variable named `scrapelyToken`. Set its value to your token.
2. Open an Agentflow, add an **Agent** node, and under **Tools** add a **Custom MCP** tool.
3. Set **MCP Server Config** to:

```json
{
  "url": "https://mcp.scrape.ly",
  "headers": {
    "Authorization": "Bearer {{$vars.scrapelyToken}}"
  }
}
```

4. Click **Available Actions** to load the server's tools, and select the ones the agent may use, or all of them.

See [Tools & MCP](https://docs.flowiseai.com/tutorials/tools-and-mcp) in the Flowise docs for more options.

## Use the tools in a flow

Connect the **Agent** node after **Start**, then open the chat and ask:

```text
Find an Actor that scrapes Google Maps, run it for 'coffee shops in Berlin' with at most 20 results, and list the name, rating, and address of each place.
```

## What the agent can do

The agent gets the MCP server's default tools. The ones used most:

| Tool | What it does |
| --- | --- |
| `search-actors` | Find Actors in the Store by keywords. |
| `fetch-actor-details` | Read an Actor's input schema, README, and pricing before running it. |
| `call-actor` | Run an Actor with a JSON input, optionally with `maxItems` and `maxTotalChargeUsd`. |
| `get-actor-run` | Wait for a run and check its status. |
| `get-actor-output` | Read a run's results, paged and kept compact. |

The full list, including saved inputs and automations, is on the [MCP server](https://scrape.ly/docs/mcp.md#tools) page. To run one Actor you already know, name it in the prompt, for example `Run username/actor-name`, so the agent skips the search.

**Costs**: runs started by the agent are billed like any run. Put the limits in the prompt (such as "at most 20 results"), and keep a **Max charge per day** on the key.

---

- Previous: [Langflow](https://scrape.ly/docs/langflow.md)
- Next: [Amazon Bedrock](https://scrape.ly/docs/amazon-bedrock.md)
- All docs: [Docs index](https://scrape.ly/docs.md), [llms.txt](https://scrape.ly/llms.txt)