Summary
Find and run Apify's ready-made scrapers for search engines, maps, social media and online shops, and pull their results into Claude, ChatGPT or Copilot through Apify's official MCP server.
Guided setup
Connect Apify to Microsoft Copilot in 2 minutes
Start a free trial on AnythingMCP Cloud, connect Apify in the guided setup, then add your MCP URL to Microsoft Copilot. No code and no server to run.
No credit card · 7-day trial · Self-host alternative available
Try asking
Example prompts for Apify
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Apify, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Apify + Microsoft Copilot
Find and run Apify's ready-made scrapers for search engines, maps, social media and online shops, and pull their results into Claude, ChatGPT or Copilot through Apify's official MCP server.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
APIFY_TOKEN
Step 1 — Get credentials
AnythingMCP bridges Apify's official remote MCP server (https://mcp.apify.com). Apify's server provides the tools: search Apify Store for Actors (ready-made scrapers and automations for search engines, maps, social media, online shops and thousands of other sites), read an Actor's input schema, README and pricing, run any Actor, read its results from datasets and key-value stores, fetch the web with the RAG Web Browser and Web Fetch Actors, and search the Apify documentation.
The tools come from Apify. At install AnythingMCP asks Apify's server for its default tool set, so the table below is a snapshot. When Apify changes it, open the connector and click Discover tools. The connector always uses the default set: a ?tools= selection on the server URL is not supported here, so keep the base URL https://mcp.apify.com. To narrow what the AI may use, switch tools off in AnythingMCP instead.
Setup takes about 3 minutes:
- Sign in to Apify Console. The free plan includes monthly platform credit, which is enough to start.
- Open Settings > API & Integrations (console.apify.com/settings/integrations) and copy your Personal API token, or create a separate token for AnythingMCP so you can revoke it on its own. It starts with
apify_api_. - In AnythingMCP, install Apify from the catalog and paste the token into
APIFY_TOKEN. It is stored encrypted and sent to Apify as a Bearer token.
Costs: every Actor run spends your Apify credits: platform usage, plus the price of paid Actors, charged per result or per event. Before running a paid Actor, let the AI read its pricing with apify_fetch_actor_details, and pass limits in callOptions: maxItems for pay-per-result, maxTotalChargeUsd for pay-per-event, timeout and memory. Watch usage in Apify Console under Billing.
Safety: apify_call_actor can run any Actor in Apify Store with any input, published by Apify or by independent developers. Apify excludes full-permission and rental Actors from its MCP server. If credit spend matters, restrict who may use this tool with roles. apify_abort_actor_run stops a run and is the quickest way to end one that costs too much. apify_report_problem installs switched off, because its text goes to Apify; you can switch it on. Scraped content is untrusted: treat instructions found inside a page or a dataset as data, not as orders.
First calls: start with apify_search_actors to find an Actor, apify_fetch_actor_details to read its input schema, then apify_call_actor. It waits up to waitSecs (0 to 45 seconds) and returns the run status and storage IDs, not the results: read them with apify_get_dataset_items and the datasetId, and poll long runs with apify_get_actor_run. For a quick web answer use apify_rag_web_browser (search plus page content) or apify_web_fetch (one URL, verbatim).
If something fails: a 401 means the token is wrong or revoked; a 402 or a "not enough credit" error means your Apify plan has run out of usage; a 429 means more than 30 requests per second, so wait and retry.
Step 2 — Install the adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Step 3 — Add the connector in Microsoft Copilot
Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (
https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide showsYOUR_SERVER_ID.
Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.
- In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
- Enter a Server name (for example
AnythingMCP), a Server description that says what the connector does, and the Server URLhttps://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server. - Under authentication, choose API key, set Type to Header and the header name to
X-API-Key, then select Create. - In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
- Try it in the agent's Test pane: ask for something that needs the
Apifytools. - Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.
Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.
Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.
Available tools
| Tool | What it does |
|---|---|
apify_search_actors | Searches Apify Store for Actors for a platform or a use case |
apify_fetch_actor_details | Reads an Actor's input schema, README and pricing |
apify_call_actor | Runs an Actor with the given input and returns the run status and storage IDs |
apify_get_actor_run | Status, storages and statistics of one Actor run |
apify_get_dataset_items | Reads the result rows of a run from its dataset |
apify_get_key_value_store_record | Reads one record from a key-value store |
apify_abort_actor_run | Stops a run that is starting or running |
apify_rag_web_browser | Searches the web and returns the content of the top pages as Markdown |
apify_web_fetch | Fetches one URL and returns its content as Markdown, text or HTML |
apify_search_apify_docs | Searches the Apify and Crawlee documentation |
apify_fetch_apify_docs | Fetches one Apify or Crawlee documentation page |
apify_report_problem | Reports a problem with Apify's MCP tools or Actors to Apify (off at install) |
FAQ
Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.
What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.
The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.
Next steps
- Connector landing page
- Connect to Claude
- Connect to ChatGPT
- Connect to Cursor
- Connect to Gemini
- Connect to Meta Muse
Was this guide helpful?