Scraping MCP server pricing: credits, events and your own infra

Prices for scraping MCP servers change often, so this guide does not restate them. It explains the shapes behind the prices: what unit you are billed in, what happens when a call fails, and how to estimate a month before you commit. Every pricing fact below links to the vendor's own page and was checked on 2026-10-27. For current numbers, open the vendor's pricing page.

Pricing shapes

Credits per request

Firecrawl bills in credits. Its pricing page lists one credit per page for scrape and crawl, one per map call, and extra credits for features such as JSON output, search results and browser interaction minutes. Plans differ in monthly credits, and its page states that only some plans carry unused credits forward. If the credit shape is the reason you are looking elsewhere, the Firecrawl MCP alternatives guide lists options by reason to switch.

Good for: steady workloads where you can count pages ahead of time. Watch for: feature add-ons that multiply the per-page cost.

Pay per event and pay per usage

Apify's MCP server exposes Actors as tools, and each Actor has its own pricing model. Apify's docs describe pay per event, where the Actor's author defines billable events such as a result or a start, and pay per usage, where you pay for the platform resources a run consumes. Pay per event Actors let you set a maximum charge per run.

Good for: jobs a specific ready-made Actor already solves. Watch for: pay per usage is harder to estimate; Apify's own docs suggest testing on a small scope first.

Credits per successful page

Single-page content APIs often charge per page read. Live Web Data API charges credits per successful page, with more credits when a page sat behind bot protection or was rendered in a browser; failed or blocked requests cost nothing. The current plans are on the pricing page. Jina's read_url works without a key at a lower rate limit, and a key raises the limits.

Good for: agents that read known public pages. Watch for: these APIs do not crawl, and Live Web Data API's MCP tool does not render JavaScript, so jobs that need either belong elsewhere.

Self-hosted infrastructure

Playwright MCP, Crawl4AI and Scrapling cost nothing to license under their open-source terms. You pay for machines, browser memory, bandwidth and, mostly, the hours someone spends running them. The hosted vs self-hosted guide covers that operating work.

What a failed call costs

Failure rules matter more than list prices for agents, because agents retry. Three cases cover it:

Whatever the rule, give the agent errors it can act on so it stops retrying URLs that will never work. The output and token cost guide covers error wording.

Free tiers as an entry point

Free tiers are good for the rubric's test step: one known page and one 404 on example.com, read through your real client. They are a poor basis for a production estimate, because rate limits on free access are usually lower and terms change. Treat any "free scraping MCP server" list as accurate only on its check date.

Estimating your month

Use four numbers:

1. Pages per day the agent will actually read, not the number it could.
2. Failure rate, from a test run against your real URL list.
3. Units per page, from the vendor's pricing page, including add-ons you will use.
4. Retries per failure your agent or client makes.

Monthly units are roughly pages × 30 × units per page, plus failures × retries × the cost of a failed call. Run the same numbers for two shapes before you pick one. A server that is cheaper per page can cost more if it charges for every failed retry.

If a content API fits

Live Web Data API appears in these tables. Its MCP server reads one public page per call and does not render JavaScript, crawl or search. Sign-up is for businesses only. Only Business, Enterprise and Custom sign-ups are reviewed before checkout, usually within 1 business day. To see how its credits work, read the MCP docs.