Disclosure: This article was drafted with AI assistance and checked against each vendor's official pages. We may receive a commission if you sign up through the ScraperAPI † or Firecrawl † links marked † in this article, at no extra cost to you. ScrapingBee is linked without a referral link. See our Advertising Disclosure.

Vendors price in credits, but an agent loop thinks in requests. Before letting one run unattended, it helps to know what a thousand of its requests would cost on each service. Below is a four-step worksheet, with the arithmetic done for three monthly volumes, using figures read from official pricing pages and docs.

Note on experience: we have not run production workloads on these services and say nothing about speed, success rates or data quality. Everything below is arithmetic on figures read from official pricing pages and docs on November 10, 2026. Prices change; check the live pages before you buy.

1. Credits per request, as documented

† marks a referral link. "Not stated" means the page we read did not say.

The defaults are different kinds of call. ScrapingBee's default renders JavaScript (5 credits); ScraperAPI's 1-credit call is its flat, non-rendered request. Putting "1" next to "5" without that context overstates the gap. Failed requests are billed differently by each service (ScraperAPI states it charges only for 200 and 404 responses), and we do not model failures.

2. Plans that cover your credits

Monthly-billed prices, before tax, from each pricing page. Larger tiers exist on all three.

Free offers as listed: Firecrawl's Free plan gives 1,000 credits and its FAQ says they recur monthly; ScrapingBee offers 1,000 free API credits with no card; ScraperAPI's pricing page shows a 7-day, 5,000-credit trial with no card, while its FAQ separately mentions a free plan of 1,000 credits, so confirm which applies. Concurrency limits differ by plan and are not modelled.

3. The worksheet

1. Write down your monthly request volume.
2. Multiply by credits per request (table 1) to get credits needed.
3. Pick the cheapest plan whose monthly credits cover that number (table 2).
4. Divide the plan price by your request volume, then multiply by 1,000.

The examples use each service's default call (ScraperAPI 1 credit, ScrapingBee 5, Firecrawl 1). They ignore retries, overages and concurrency, and they pay the full plan price even if you use part of it.

Two patterns fall out of the published prices (they say nothing about how well any service works). At small volumes the minimum plan price dominates, so a cheap entry plan beats a cheap per-credit price. At larger volumes both the per-credit price and the credits-per-request multiplier matter, and the cheapest service for one call type can lose for another.

If you want to try a free offer while measuring your own request mix, the ScraperAPI † and Firecrawl † signup links support this site. The original post has a small calculator you can edit with your own numbers. Related reading: ScraperAPI vs ScrapingBee, Firecrawl Credits Explained and Free Tiers of Web-Data Tools Compared.

4. What this worksheet leaves out

• ScrapingBee's cost without JavaScript rendering: not stated on the page we read.
• Per-domain surcharges (ScraperAPI lists higher credit costs for e-commerce, search-engine and social-media domains) and bot-protection add-ons.
• Failed-request billing, retries, overage pricing, annual discounts and VAT.
• Concurrency, which can force a larger plan than your credit count suggests.
• Success rates, speed and data quality. We have not measured them, and a cheaper request that fails more often can cost more per usable page.
• These pages were read through a web-fetch tool that summarises pages, not a manual read of the rendered pages. Confirm against the live pages before buying.

Sources (checked November 10, 2026)

• ScraperAPI pricing
• ScraperAPI docs: credits and request costs
• ScrapingBee pricing
• ScrapingBee documentation
• Firecrawl pricing
• Firecrawl docs: billing

Disclosure: This article was drafted with AI assistance. We may receive a commission if you sign up through the Bright Data † link or the ScraperAPI † link marked † in this article, at no extra cost to you. We have not run Bright Data's MCP server ourselves; everything below comes from Bright Data's official pages and the project README. See our Advertising Disclosure.

Connecting an AI client to a metered web-data service is easy; knowing what it can spend is the part people skip. Bright Data's Web MCP offers search and page-fetch tools to clients such as Claude Desktop or Cursor, and its product page advertises a free monthly allowance. This checklist collects what the vendor documents about limits and billing, and what it leaves unstated.

Note on experience: we have not used this server in production and we do not claim results. Facts below were read from the pages listed in the sources on November 10, 2026. Where a page did not say, we write "not stated".

1. What the vendor documents

† marks a referral link (see the disclosure above).

If you want an account to try this, you can start from Bright Data †. The free allowance above is what the vendor documents; re-read it on their page before relying on it, since terms can change.

2. The checklist

1. Treat the API token like a password. The hosted URL puts the token in a query string. Query strings can end up in logs and shell history, so keep the full URL out of shared configs and repositories. (General practice, not a statement from Bright Data.)
2. Turn off tools you do not need. The docs describe groups and tools parameters on the remote URL, and GROUPS or TOOLS environment variables for a local run. The overview says choosing only the tools you need helps reduce context size and token usage. Fewer tools also makes it easier to reason about what an agent can spend.
3. Know the groups. The tools page lists: all (search_engine, scrape_as_markdown, ask_brightdata_assistant), advanced_scraping (batch search and scrape, session_stats), scrapers (search, run and fetch results from prebuilt scrapers), social and business (dataset search), browser (a set of scraping_browser_* tools such as navigate, click, type and screenshot) and geo (chatgpt_ai_insights, perplexity_ai_insights).
4. Read the billing notes on the scraper tools. The tools page says run_scraper is "Billed per record" and that in the scraper workflow "Every record is billed." Those lines are about records, not about the 5,000 request figure, and the page does not connect the two.
5. Consider a rate limit. The README lists a RATE_LIMIT setting (default unlimited, with 100/1h as the example format). An agent that loops can burn a monthly allowance quickly; a cap in the client config is a cheap guard.
6. Check the browser zone name if you enable browser tools. The README lists BROWSER_ZONE with a default of mcp_browser. The docs do not say whether browser sessions count against the free allowance.
7. Check the dashboard after the first session. Compare what you expected an agent to use with what the account shows, before leaving it running unattended.

3. What we could not confirm

• Which tools count toward the free 5,000: the tools page does not state it.
• Pay-as-you-go prices for MCP usage after the free tier, and whether the free allowance carries over between months (rollover is not stated on the pages we read).
• Rate limits on the hosted server (the docs overview does not state them).
• Rapid and Pro modes: not stated on the pages we read.
• Any measure of success rate, speed or result quality. We have not tested the service.

4. Where this fits

For a side-by-side of how the MCP servers from Apify, Firecrawl, Bright Data, ScraperAPI and ScrapingBee connect and sign in, read Web-Data MCP Servers for AI Agents, Compared. For free allowances across the wider tool set, see Free Tiers of Web-Data Tools for AI Agents, Compared. If you would rather size an HTTP scraping API by cost, the cost-per-1,000-requests worksheet uses ScraperAPI † among others.

Sources (checked November 10, 2026)

• Bright Data Web MCP product page
• Bright Data MCP docs overview and tools
• brightdata-mcp README

Disclosure: This article was drafted with AI assistance and checked against each vendor's official documentation. We may receive a commission if you sign up through the ScraperAPI † or Firecrawl † or Bright Data † links marked † below, at no extra cost to you. We have not tested these servers ourselves. Our applications to Apify and ScrapingBee are still pending, so links to those go to the official sites. See our Advertising Disclosure.

The Model Context Protocol (MCP) lets an AI client such as Claude Desktop, Cursor or VS Code call external tools. Most web-data vendors now ship an MCP server, so an agent can fetch a page or run a search without glue code. The servers differ in how you connect, how you sign in, and how much of the tool list is documented. This page compares five of them.

Note on experience: we have not run any of these servers in production. Facts below are from the vendor pages linked in the sources, read on November 8, 2026. Where a page did not say, we write "not stated" rather than guess.

1. At a glance

† marks a referral link.

2. Tools each server documents

• Apify: enabled by default are search-actors, fetch-actor-details, call-actor, apify/rag-web-browser, apify/web-fetch, search-apify-docs, fetch-apify-docs and report-problem. Optional categories cover Actor runs, datasets, key-value stores, tasks and schedules. The rate limit is stated as up to 30 requests per second per user (HTTP 429 beyond that).
• Firecrawl: firecrawl_scrape, firecrawl_map, firecrawl_search, firecrawl_parse, firecrawl_crawl, firecrawl_check_crawl_status, firecrawl_agent, firecrawl_agent_status, firecrawl_interact and firecrawl_interact_stop, plus groups for research, developer search, government search and monitors. The old Extract tool is described as deprecated.
• Bright Data: 30 tools in total according to the project README, in groups named scrapers (6), browser (14), geo (2) and advanced_scraping (3). Every group also includes search_engine, scrape_as_markdown and ask_brightdata_assistant. You can limit the exposed tools with groups or tools parameters to keep the client's context small.
• ScraperAPI: the MCP page says it supports ScraperAPI parameters such as geotargeting, premium proxies and JavaScript rendering. It does not list tool names.
• ScrapingBee: HTML tools (get_page_text, get_page_html, extract_page_data, get_screenshot, get_file), search and AI tools (fast_search, get_google_search_results, ask_chatgpt, ask_gemini), Amazon and Walmart tools, YouTube tools, and get_scrapingbee_usage (limited to 6 calls per minute).

3. Which clients are named

• Apify: Claude Desktop and VS Code extensions with MCP support; any client implementing the MCP specification should work. The page also points to a plugin for coding agents such as Claude Code, Cursor, GitHub Copilot and Codex.
• Firecrawl: ChatGPT and Codex, Claude (including Claude Desktop and Claude Code), GitHub Copilot CLI and VS Code.
• Bright Data (README): Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, Zed and Warp, plus any client that supports local MCP servers.
• ScrapingBee: Claude Desktop and Cursor via npx mcp-remote, ChatGPT through a custom app (plan limits apply), and any client that supports MCP over streamable HTTP.
• ScraperAPI: not stated on the page we read.

4. Things to check before you connect

• Where the key lives. ScrapingBee's page notes that the API key sits in the URL, so keep that config out of source control and rotate the key if it leaks. Bright Data's remote URL, as written in its README, also carries a token in the query string. Apify's default flow uses OAuth so the token stays out of the client config.
• How many tools your client loads. A long tool list takes context. Bright Data documents group and tool filters for this reason.
• Which meter runs. Apify bills platform usage, Firecrawl bills credits, Bright Data counts requests, ScrapingBee charges the same credits as the matching API call.
• Concurrency and rate limits. ScrapingBee's hosted server has a shared global concurrency limit and may return HTTP 429; Apify states 30 requests per second per user.

5. A neutral way to choose

• Try an MCP server without an account: Firecrawl documents a keyless mode with daily limits, and Apify's docs and Actor-search tools work without a token.
• Most documented tool surface and filters: Bright Data lists 30 tools in named groups.
• A specific site or marketplace: ScrapingBee lists Amazon, Walmart and YouTube tools; Apify's Actor catalog is its equivalent.
• You already use an HTTP scraping API and want the same engine in your agent: ScraperAPI † and ScrapingBee both document MCP servers on top of their APIs.

6. What we could not confirm

• ScraperAPI MCP: tool names, supported clients, authentication and credit usage.
• Bright Data: the product page and the docs overview did not state the endpoint, tool count or authentication; those details come from the project README.
• Firecrawl: credit cost per MCP tool (only Alexandria discovery is stated as free) and the numeric keyless daily limits.
• Real-world reliability, latency and result quality of any of these servers; we have not measured them.

Sources (checked November 8, 2026)

• Apify MCP server docs
• Firecrawl MCP server and tools
• Bright Data Web MCP, docs overview and the project README
• ScraperAPI MCP server docs
• ScrapingBee Remote MCP docs

Disclosure: This article was drafted with AI assistance and checked against Apify's official pages. We have applied to Apify's affiliate program and the application is still pending. Today every link to Apify here goes to its official site and is not a tracked referral link. If that changes and we earn a commission, it costs you nothing extra. See our Advertising Disclosure.

"Free" on a pricing page rarely tells you what you can actually do before the meter stops. Apify's free plan gives you $5 of platform usage per month, and that number only becomes useful once you convert it into something concrete: how long a scraper can run, and how many times.

Note on experience: we have not run production workloads on Apify. Everything below comes from Apify's own pricing page and its usage and resources documentation, both checked on November 8, 2026. The arithmetic is ours and is shown so you can check it.

1. What the free plan includes (per Apify's pricing page)

The first paid tier, Starter, is listed at $19 per month ($17 per month billed annually) with $19 of included usage, the same $0.20 per CU, 64 GB max memory and 32 concurrent runs.

2. Turning dollars into run time

Apify bills Actor runs in compute units. Its documentation gives this example: running an Actor with 1024 MB of memory for 1 hour consumes 1 CU, and CUs are calculated by multiplying memory by duration. At $0.20 per CU, the $5 credit equals 25 CU.

If the whole credit went to compute, that would buy:

Memory also sets CPU. Per the documentation, every 4096 MB of memory gives the Actor one full CPU core, with smaller allocations scaled proportionally (512 MB is 1/8 of a core). So the cheap option is not free of trade-offs: a 512 MB run is slower than a 4096 MB run on CPU-bound work.

3. Worked examples

The formula is memory (in GB) × hours × $0.20 per CU. It ignores everything else that can appear on a bill. (The original article has a small interactive calculator; here are worked examples from the same formula.)

• A 10-minute run at 1024 MB is 1/6 CU (about $0.033), so roughly 150 runs fit in $5.
• A 10-minute run at 4096 MB is about 0.67 CU ($0.13), so roughly 37 runs.
• A 2-minute run at 512 MB is about $0.0033, so roughly 1,500 runs.

4. What this estimate leaves out

• Other line items. Apify's pricing page lists residential proxy at $8 per GB and SERPs at $2.50 per 1,000 on the free plan, and describes Store Actors priced per event, per usage, or both (one example shown is $2.30 per 1,000 results). We did not verify how these are drawn against the $5 credit, so treat the table above as a ceiling for compute alone, not a promise.
• Proxy limits. The page states that the free plan includes Apify Proxy limited to use within the platform and not for external clients.
• Third-party summaries disagree. Pricing roundups we saw in search results list different Starter prices and memory limits from each other. We used only Apify's own page; check it again before you rely on any number here, because plans change.

5. Is the free plan enough?

It is a reasonable place to find out whether Apify fits your workflow: a few hundred short test runs, or a few dozen heavier ones, fit inside the credit under the formula above. It is a poor fit if your agent needs a steady, always-on scraper, because the credit is a monthly cap and access is blocked once it is spent. If you are still deciding between a general automation hub and a scraping-specific platform, read our comparison: Make vs Apify: Which Should You Try First?

Sources (checked November 8, 2026)

• Apify pricing — plan prices, $5 free usage, $0.20 per CU, limits, no credit card, no rollover, access blocked when exhausted
• Apify docs: usage and resources — CU example (1024 MB for 1 hour = 1 CU), memory-to-CPU ratio