The server itself exposes 19 tools, and some of them can write to your Apify account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Apify.

How is this different from connecting Apify MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Apify MCP API changes?

We track the Apify MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Apify tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Apify?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Apify MCP server myself?

No. TrustGate connects to the Apify MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Apify directly.

Connect Apify MCP to your AI agents, securely.

One secured endpoint for every Apify call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Apify MCP now

What your agents can ask once Apify MCP is connected.

“Find the latest news about autonomous AI agents and summarize the key developments”
“Scrape the top 10 restaurants in Prague from Google Maps with their contact details”
“Search the Apify Store for an Instagram scraper and show me its input schema”

“Show me the next 10 results from that scraping run”
“Why did this Actor run fail? Show me the log”
“What datasets do I have and how big are they?”

Select the tools your AI agents can call

19 tools from the Apify MCP schema.

Showing 19 tools

search-actorsreadSearches for Actors in the Apify Store. Usable without an API token.
fetch-actor-detailsreadRetrieves detailed information about an Actor, including its input schema, README, pricing and output schema. Usable without an API token.
call-actorhigh riskCalls an Actor and returns its run results. Executes third-party code against external sites and costs money per run. The response carries run metadata and storage IDs, not the dataset items.
get-actor-runreadGets detailed information about a specific Actor run. Auto-injected when call-actor or an Actor tool is present.
get-actor-run-listreadGets the list of an Actor's runs, filterable by status.
get-actor-logreadRetrieves the logs for a specific Actor run.
abort-actor-runwriteAborts a running Actor run, optionally gracefully. Auto-injected alongside call-actor.
get-dataset-itemsreadRetrieves items from a dataset with filtering and pagination. This is the follow-up call that returns the actual scraped data.
get-datasetreadGets metadata about a specific dataset.
get-dataset-schemareadGenerates a JSON schema from dataset items.
get-dataset-listreadLists all datasets available to the user.
get-key-value-store-recordreadGets the value associated with a key in a key-value store. Auto-injected alongside call-actor.
get-key-value-storereadGets metadata about a specific key-value store.
get-key-value-store-keysreadLists the keys within a specific key-value store.
get-key-value-store-listreadLists all key-value stores available to the user.
search-apify-docsreadSearches the Apify documentation for relevant pages. Usable without an API token.
fetch-apify-docsreadFetches the full content of an Apify documentation page by URL. Usable without an API token.
apify--rag-web-browserhigh riskThe pre-configured Actor tool: searches the web, scrapes the top N URLs and returns their content. Reaches arbitrary external sites and costs money per run.
report-problemwriteReports a problem with an Apify tool or Actor to the Apify team.

What Apify MCP exposes

Apify MCP groups its 19 tools into 6 categories, each with a suggested starting policy.

Category	Covers	Access	Suggested policy
Storage	Dataset items with filtering and pagination, dataset and store metadata, generated schemas, key-value records and keys, and the lists of datasets and stores	Read	Actor calls return run metadata and storage IDs but no items; get-dataset-items is the follow-up that actually reads the data
Runs	Run details, the list of runs filterable by status, run logs and aborting a running Actor	Read / Write	Aborting stops work already paid for; approve it
Actors	Searching the Apify Store, fetching an Actor's input schema, README, pricing and output schema, and calling an Actor	Read / Write	call-actor carries the openWorldHint annotation: it executes third-party code against external sites and costs money per run
Documentation	Searching the Apify documentation and fetching a page by URL	Read	One of the four tools usable without an API token; safe to allow broadly
Actor Tools	Any Apify Actor loaded as its own tool, with its input schema turned into the tool's parameters. The server ships pre-configured with the RAG Web Browser	Read / Write	Each Actor becomes a distinct tool name, so an allowlist must be updated whenever the tools parameter changes
Dev	Reporting a problem with an Apify tool or Actor to the Apify team	Read / Write	Served by default only when telemetry is enabled; exclude it with an explicit tools list