Our grade: 4 checks
Based on public data, not a full audit. See how we grade. Something changed? Request a re-grade.
Community rating
- 5 4
- 4 4
- 3 1
- 2 0
- 1 0
Trust in production
- Trust it - 89%
- With caveats - 11%
- Wouldn't - 0%
100% would recommend this server
How reviewers scored it
- Setup & docs 4.1
- Auth experience 4.1
- Reliability 4.1
- Maintainer responsiveness 4.6
Why it got an A
Apify's official open-source server, hosted over HTTPS with OAuth and released several times a week. Actors run on Apify's cloud, not your machine, but many are written by third parties, read pages the model picks and cost credits; cap spend with maxTotalChargeUsd or maxItems. Three 2026 advisories, including a token leak (CVE-2026-50143), were fixed before they were published (use 0.18.1 or later locally). Biggest deduction: OAuth and API tokens act for your whole Apify account with no scopes; limit tools with the tools parameter instead.
How to connect
# Apify CLI writes the Cursor config, including your API token
apify mcp install cursor
// VS Code MCP configuration (.vscode/mcp.json)
{ "servers": { "apify": { "type": "http", "url": "https://mcp.apify.com" } } }
claude mcp add apify "https://mcp.apify.com" -t http
Is Apify MCP Server safe?
Is Apify MCP Server safe to use?
Apify MCP Server grades A (strong public trust signals). Login is required, but access is coarse: one sign-in or key covers more than your agent needs, so grant the narrowest account you can.
Does Apify MCP Server have known vulnerabilities?
Not in our current data: it has no open CVEs or advisories. We re-check as new ones are published.
Does Apify MCP Server support authentication?
Yes. It requires a login, so access can be tied to a person or a scoped key.
Alternatives in Browser & Web Automation
- C BrowserTools MCPGive your coding agent the console logs, network requests, screenshots and Lighthouse audits from the Chrome tab you already have open.
- C Chrome DevTools MCPLet an agent drive and debug a live Chrome with DevTools, including performance traces, network, console, screenshots, and scripts.
- C Playwright MCPDrive a real browser to navigate, click, fill, and extract via MCP.
- C browser-use MCPLLM-oriented browser automation with a high-level action API.
Community reviews
Solid and well behaved
Tried it on a side project first, then rolled it out at work. Nice that it supports both stdio and HTTP, I use stdio locally and HTTP for the shared agent. Scoped the token to just what the agent needs and it respected that. Updates land regularly, and nothing broke when I upgraded.
Used for QA smoke tests after deploys
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 5/5
Quietly reliable
Set this up for our team after comparing a few options. You can tell it is actively maintained, the rough edges keep getting fixed. I like that access goes through a proper sign-in instead of a long-lived secret on disk. It is in our production agent and I sleep fine.
Used for Scraping public pricing pages
- Setup & docs 5/5
- Auth experience 3/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Does what it says, no drama
Of the Apify integrations I tried, this one is the most predictable. Auth is handled properly, and revoking access later was one click. Easy recommendation.
Used for QA smoke tests after deploys
- Setup & docs 3/5
- Auth experience 5/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Easy win for our agent setup
I use this almost daily. Nice that it supports both stdio and HTTP, I use stdio locally and HTTP for the shared agent. Releases come often and the changelog is clear. Nice to use something maintained by Apify rather than a random fork.
Used for Visual regression checks
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Clean integration, sensible permissions
Simple to set up in Cursor, simple to reason about. Releases come often and the changelog is clear. Sign-in flow was painless and I never had to paste a key into a config file. The OAuth flow worked first time in Claude Code.
Used for Collecting screenshots for bug reports
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Set it up once, forgot about it
Hooked Apify MCP Server into Claude Code and it worked on the first try. Sign-in flow was painless and I never had to paste a key into a config file. Would recommend without hesitation.
Used for Research agent browsing documentation
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Our team uses it every day
Replaced a homegrown script with Apify MCP Server and have not looked back. Scoped the token to just what the agent needs and it respected that. Token setup is the fiddliest part, after that it is smooth. Updates land regularly, and nothing broke when I upgraded. Happy to run it in production.
Used for Monitoring a competitor changelog
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Recommended it to two teams already
Clear tool names, sensible outputs, very few surprises. Auth is handled properly, and revoking access later was one click. You can tell it is actively maintained, the rough edges keep getting fixed.
Used for End-to-end test runs against staging
- Setup & docs 4/5
- Auth experience 5/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Solid core, fiddly setup
Took longer to configure than I expected. Auth is handled properly, and revoking access later was one click. Filed an issue and got a reply within two days. Fine in production if you sandbox it.
Used for Filling repetitive web forms
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Write a review
Ran this server? Tell other teams how it went. You get one review per server. We email you a link to confirm it, then an editor checks it before it goes up. We never show your email.