Integrations

Upsonic

Give Upsonic agents tools that run Actors and read their results.

Give Upsonic agents Scrape.ly tools: search the Store, run Actors, wait for their runs, and read the results. Agents connect to the hosted MCP server through Upsonic's MCPHandler, so there is no Scrape.ly package to install.

.bash

pip install "upsonic[mcp]"

Create an API token in the dashboard under Settings → API & Integrations and set it as SCRAPELY_TOKEN. 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.

Give an agent Scrape.ly tools

Open the server with MCPHandler and add it to the task's tools. StreamableHTTPClientParams sends the token with every request.

.python

import os
from datetime import timedelta

from upsonic import Agent, Task
from upsonic.tools.mcp import MCPHandler, StreamableHTTPClientParams

scrapely = MCPHandler(
    server_params=StreamableHTTPClientParams(
        url="https://mcp.scrape.ly",
        headers={"Authorization": f"Bearer {os.environ['SCRAPELY_TOKEN']}"},
        timeout=timedelta(seconds=30),
        sse_read_timeout=timedelta(seconds=300),
    ),
    timeout_seconds=60,
)

task = Task(
    description=(
        "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."
    ),
    tools=[scrapely],
)

agent = Agent(name="Web researcher", model="anthropic/claude-sonnet-5-5")
agent.print_do(task)

Any model Upsonic supports works. See MCP tools for more options.

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 page. To run one Actor you already know, name it in the task, 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 task (such as "at most 20 results"), and keep a Max charge per day on the key.