This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
An MCP server for Scrape.ly. It gives AI agents and MCP clients access to a Scrape.ly account: search the Store for Actors, read their README and input schema, run them, follow the runs, and read the results from datasets, key-value stores and logs. It can also manage saved tasks and search the Scrape.ly and Crawlee documentation.
Full documentation: scrape.ly/docs/mcp.
The same package runs in two ways:
Hosted: scrapely-mcp-http, a multi-tenant streamable HTTP server. Scrape.ly runs it behind the API at
https://mcp.scrape.ly. Most users connect to that URL and never install anything.
Local: scrapely-mcp-server, a stdio server started by a desktop MCP client on your machine.
Point your client at https://mcp.scrape.ly.
Clients that support MCP authorization find the OAuth flow on their own and ask you to sign in.
Otherwise send your API token as a header: Authorization: Bearer <token>.
Clients that cannot set headers can append ?token=<token> to the URL. URLs tend to end up in logs, so prefer
the header.
Example for a client that takes a JSON config:
{
"mcpServers": {
"scrapely": {
"url": "https://mcp.scrape.ly",
"headers": { "Authorization": "Bearer YOUR_TOKEN" }
}
}
}Related MCP server: AXE Fleet MCP Server
Requires Python 3.11 or newer.
uvx --from scrapely-mcp scrapely-mcp-server
# or
pip install scrapely-mcp
scrapely-mcp-serverThe token comes from SCRAPELY_TOKEN, or from the token field of ~/.scrapely/credentials.json or
~/.scrapely/auth.json. A token is required unless every selected tool works without one
(search-actors, fetch-actor-details and the docs tools).
{
"mcpServers": {
"scrapely": {
"command": "uvx",
"args": ["--from", "scrapely-mcp", "scrapely-mcp-server"],
"env": { "SCRAPELY_TOKEN": "YOUR_TOKEN" }
}
}
}Options:
Flag | Meaning |
| Tool categories or tool names to enable. Replaces the default set. |
| Expose these Actors as their own tools. |
| MCP Apps widget mode (widgets are disabled in this release, see below). |
| Opt in to usage telemetry (also needs a write key, see below). |
| Which telemetry write key variable to use. |
Default categories: actors, docs, runs, storage, tasks, automations. The dev category (report-problem) is off by
default.
Category | Tools |
actors |
|
docs |
|
runs |
|
storage |
|
tasks |
|
automations |
|
dev |
|
search-scrapely-docs searches the Scrape.ly docs at scrape.ly/docs by default
(docSource: "scrapely"), or the Crawlee docs (crawlee-js, crawlee-py). fetch-scrapely-docs returns a page as
Markdown; it accepts pages under https://scrape.ly/docs and https://crawlee.dev.
Whenever call-actor, get-actor-run or an Actor tool is enabled, get-actor-run, get-actor-output,
get-dataset-items, get-key-value-store-record and abort-actor-run are added as well.
call-actor waits up to waitSecs (0 to 45, default 30) and returns the run status and storage IDs; the agent then
fetches the results with get-actor-output (pass the runId, or a datasetId). It returns a page of dataset items
(offset, limit up to 1000, default 100, and fields with dot notation) plus the run's OUTPUT record. Long text
values are cut and a page may hold fewer items than limit so the reply stays small; hasMore and nextOffset say
where to continue. get-dataset-items remains available for finer control. Clients that support protocol tasks can run call-actor as a long-running task
and collect the result when the run ends. Progress notifications are sent while a run is awaited, and cancelling the
request aborts the run.
Any Scrape.ly API GET endpoint can also be read with resources/read using its full URL, for example
https://api.scrape.ly/v2/datasets/<id>/items?limit=20.
scrapely-mcp-http --host 0.0.0.0 --port 8000Path | Purpose |
| MCP endpoint (streamable HTTP; 2026-07-28 stateless requests are also served) |
| OAuth protected-resource metadata (also under |
| Health check, |
URL parameters on the MCP endpoint: tools, actors, maxActorMemoryBytes, ui, payment (skyfire or
x402), telemetry-enabled, token.
Each session gets its own server instance bound to the SHA-256 fingerprint of the credential that opened it; a
request with a different credential is answered as if the session did not exist. SCRAPELY_TOKEN is never used by
the HTTP server.
A container image definition is in Dockerfile (docker build --build-arg SOURCE=local -t scrapely-mcp .).
Variable | Default | Purpose |
| none | Token for the stdio server |
|
| API origin used for outbound calls |
| derived | API origin shown to clients and used as OAuth issuer |
|
| Base of Store links |
| API origin | Base for MCP-server Actors |
|
| HTTP bind address |
| none | Default tool selection of the HTTP server |
|
| Widget mode |
|
| Idle session timeout |
|
| Session limit |
|
| Open sessions per presented token; over it the caller's own oldest idle session is closed, or the request gets 429 |
|
| Open sessions per client IP (last |
|
| Open sessions per client IPv6 /48 (the per-IP cap groups IPv6 by /64) |
|
| Most distinct Actors one |
|
| Time one tool call's argument validation may take; a call over it is refused as too large or complex |
|
| Byte limit for what one connection to an MCP-server Actor may return |
|
| Byte limit for one |
|
| Tool definitions one Actor may add to a session; an Actor over it is skipped |
|
| Actor tool definitions one session may keep; Actors past it are skipped |
|
| Actor tool definitions all sessions may keep together; a new session or request that does not fit gets 503 |
|
| Bytes all open connections to MCP-server Actors may hold together (task results until they are stored); a connection over it fails with a retry hint |
|
| Largest result one tool call (or task) may return; a larger one becomes an error |
|
| Bytes of one dataset page the storage tools read; a page is cut after its last complete item |
|
| Bytes of one key-value record read inline; a larger record is returned as a download link |
|
| Protocol tasks kept per session/credential; oldest finished ones are dropped first |
|
| Protocol tasks kept in total |
|
| Task results kept per session/credential; the oldest are released first |
|
| Task results kept in total; the oldest are released first |
|
| A task result is released this long after |
|
| Finished tasks are dropped this long after they finish (or after their |
|
| Clients that do not see |
|
| Usernames shown as maintained by Scrape.ly, only when the API sends no |
|
| Scrape.ly docs: searched through its |
| public Crawlee DocSearch values | Crawlee docs search |
| disabled | Personalised dashboard links |
| off | MCP Apps widgets (experimental) |
|
| Also send the legacy payment-protocol header |
| none | Shown in Skyfire payment hints |
|
| Session log sent to the Scrape.ly API (see below); |
| off | Opt-in telemetry |
| none | Error reporting (install the |
|
| Log level (logs go to stderr) |
Telemetry is off unless it is enabled and a write key is configured; the package ships no keys. Logs never contain tokens, payment tokens or payment signatures.
context parameterEvery tool accepts an optional context string: one or two sentences from the AI on what the user wants and why it
calls the tool. It is removed before the arguments are validated and never reaches the tool or the Actor; clients that
do not send it work as before.
The server reports each session's activity to the Scrape.ly API with your own token, so Scrape.ly can see how the MCP
server is used and what fails: the client name and version, the transport, each tool call with its arguments, the
context, the status, the duration and a short summary of the result. Values are sent and stored as they are,
nothing is masked, so do not put secrets in tool arguments you do not want Scrape.ly to see. Set
SCRAPELY_MCP_SESSION_LOG=false to turn it off.
MCP Apps widget tools (search-actors-widget, fetch-actor-details-widget, call-actor-widget,
get-actor-run-widget) are implemented but disabled by default, and no widget HTML is bundled. With widgets
disabled every client gets the plain tool set.
uv venv && uv pip install -e ".[test]"
pytestThis server cannot be deployed
Apify MCP — run web-scraping Actors and fetch their dataset results.
Scrape, crawl and search the web for AI agents via MCP.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
