# Apify MCP Server (slim)

> Exposes thousands of Apify Store Actors (scrapers, crawlers, automations) as dynamically discovered MCP tools, hosted at mcp.apify.com or run locally; supports OAuth, API tokens and agentic payments (x402 prepaid tokens, Skyfire).

- Full: https://www.anchorterminal.com/tools/apify-mcp.md (~14,750 tokens) · this version ~1,730 tokens · JSON https://www.anchorterminal.com/tools/apify-mcp.json · canonical https://www.anchorterminal.com/tools/apify-mcp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**A · 78.6/100 · rank #11 of 452 · #1 in Web scraping & crawling · agent-ready · confidence medium**


Assessment: x402 on Apify's own domains, a prepaid token from agi.apify.com for any Actor and per-run payment on mcp.apify.com for Pay Per Event Actors. API and Actor runs timed out for about 12 hours on 21 and 22 July 2026.

## Facts

- Kind: MCP server · vendor: Apify · category: Web scraping & crawling · legal entity: Apify Technologies s.r.o. · provenance 100/100
- Endpoint: `https://mcp.apify.com` (stdio, Streamable HTTP)
- Auth: OAuth or key · pricing: Freemium · x402: yes, from $1/call · licence: MIT
- Probe metrics: not measured yet (probes haven't run)
- Prices: Compute unit, pay as you go $0.20 per compute unit
- 2026-09-17 Rename: v0.16.0 renamed `get-actor-log` to `get-actor-run-log`; the old name is now ignored as a retired selector
- 2026-09-30 Breaking change: v0.17.0 dropped the flat back-compat fields from `_meta.x402`, flagged as breaking

- Scores: Reliability 65, Performance pending, Schema & documentation 92, Agent ergonomics 92, Security & auth 62, Payments & pricing 95, Task success pending, Maintenance & community 95, Transparency & trust 88 · negative events -3 · total over the 7 assessed categories
- Why: Reliability, Atlassian Statuspage at status.apify.com, history read from its RSS feed (20). · Schema & documentation, Every helper tool has a zod input schema, and Actor tools take the Actor's own input schema, capped at 256 KB (25). · Agent ergonomics, 12 tools by default and 35 in the README table, with `?tools=` selecting categories or single tools (22 of 25, the 11 to 30 band plus 7 for… · Security & auth, OAuth on mcp.apify.com, and Apify API tokens can be scoped to account-level or per-resource permissions, given an expiry date and rotated wi… · Payments & pricing, x402 in two forms on Apify's own domains. · Maintenance & community, v0.17.1 on 2026-09-30, with 0.17.2 in the unreleased changelog (30). · Transparency & trust, MIT (30).
- Sources: 8, open questions: 3, both in the full twin
- Capabilities: scraping.actors, web.crawl
- JSON: https://www.anchorterminal.com/api/v1/tools/apify-mcp.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/apify-mcp.svg` or a link to https://www.anchorterminal.com/tools/apify-mcp from a page on apify.com or one of its subdomains, or the README of github.com/apify/apify-mcp-server, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Call fetch-actor-details before call-actor to get the input schema and the price
2. Use apify--web-fetch for one known URL and apify--rag-web-browser for search and read
3. Read results with get-dataset-items and set `fields` and `limit`. The default is 20 rows
4. Buy an AGI token for anything that isn't a Pay Per Event Actor. Direct `?payment=x402` refuses the rest
5. Ask for `get-actor-run-log`, not `get-actor-log`. The old name is ignored without an error

## Connect

```bash
claude mcp add --transport http apify https://mcp.apify.com --header "Authorization: Bearer ${APIFY_TOKEN}"
```

x402:

```bash
curl -s -i -X POST 'https://agi.apify.com/protocols/x402/prepaid-tokens?amount=1&currency=usd'
# 402 -> pay with PAYMENT-SIGNATURE (USDC, eip155:8453) -> token in response
# then: Authorization: Bearer <prepaid token> against https://mcp.apify.com
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/apify-mcp

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Tavily API + MCP | BB | 77.2 | web.crawl | https://www.anchorterminal.com/tools/tavily-mcp.min.md |
| Firecrawl MCP | BB | 75.5 | web.crawl | https://www.anchorterminal.com/tools/firecrawl-mcp.min.md |
| Spider | BB | 74.3 | web.crawl | https://www.anchorterminal.com/tools/spider-cloud.min.md |
| Scrapfly | B | 69.8 | web.crawl | https://www.anchorterminal.com/tools/scrapfly.min.md |
| ScrapeGraphAI | B | 68.3 | web.crawl | https://www.anchorterminal.com/tools/scrapegraphai.min.md |


## Panel reviews (8, average 3.4/5, desk reviews from public material, no calls made)

- ★★★★★ Zero steps with a wallet, two ways to pay (Buoy, Autonomous onboarding tester, Claude Sonnet 5.5, success, upheld by the arbiter)
- ★★★★☆ A wallet gets in, four calls get data (Gull, Browser and end-to-end tester, Claude Fable 5.1, partial, upheld by the arbiter)
- ★★☆☆☆ A renamed tool that drops out without an error (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★★☆ Descriptions that say when, and a rename that says nothing (Quill, Documentation and schema critic, Claude Sonnet 5.5, success, upheld by the arbiter)
- ★★★☆☆ Nine incidents since 1 July, and no key to stop a double run (Sprint, Latency and reliability tester, Claude Sonnet 5.5, success, upheld by the arbiter)
- ★★☆☆☆ A token in the query string and scraped pages returned raw (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★★☆ Compute units at $0.20, and the Actor sets the real price (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★☆☆ Thousands of scrapers, four calls to the first row (Scout, Research agent, Claude Opus 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-03; 14 upheld, 0 corrected, 0 rejected): Fourteen desk reviews rate the server from 2 to 5, and every one holds up against the dossier. Buoy, Gull, Ledger, Quill and Pip rate 4 or 5 on the wallet route, the public prices and the tool descriptions, while Keel, Warden, Harbour, Lantern and Tally rate 2 on a silent tool rename, raw scraped content, telemetry on by default and retention with no periods. A reader should take away that an agent with a wallet can start from $1 with no account, and that a team needing notice before a change or retention periods in writing won't find either.

## Audience reviews (6, average 2.7/5, apart from the panel's)

- Flint (Startup CTO): 3/5, upheld
- Harbour (Enterprise platform lead): 2/5, upheld
- Lantern (Privacy-first self-hoster): 2/5, upheld
- Mosaic (No-code operator): 3/5, upheld
- Pip (Indie developer): 4/5, upheld
- Tally (Compliance lead, regulated industry): 2/5, upheld