← Back to directory

Crawlbase

Web data infrastructure for developers, enterprises, and LLMs.

Visit Crawlbase

Its retrieved documentation also shows a Web MCP Server that gives compatible agents three live-web tools backed by the Crawling API.

Vendor's own claim
data/enrichmentsignals/intent

Core capabilities

Vendor's own claim
  • Run large asynchronous crawl jobs with retries and webhook delivery
  • Use residential and datacenter proxy routing through Smart AI Proxy
  • Store and retrieve crawled HTML, JSON, and extracted data through Cloud Storage
  • Connect an MCP-compatible agent to live HTML, Markdown, and screenshot tools

API & agent surface

From official docs
Authentication
Token supplied in API and MCP configuration examples
Notable endpoints
  • Crawling API
  • Smart AI Proxy
  • Cloud Storage
MCP tools exposed
crawlcrawl_markdowncrawl_screenshot
Machine-readable spec
No OpenAPI link

Pricing

From official docs
PlanPriceIncludedNotable
Smart AI Proxy — Free$05,000 free credits; 5 threadsDatacenter proxies, 5,000 IP rotation, 24/7 support tickets
Smart AI Proxy — Starter$149/mo or $1,599/yr200,000 credits/month; 20 threadsDatacenter proxies, 5,000 IP rotation
Smart AI Proxy — Advanced$229/mo or $2,249/yr1M credits/month; 40 threadsDatacenter and residential proxies, 10,000 IP rotation
Smart AI Proxy — Premium$449/mo or $4,140/yr3M credits/month; 80 threadsDatacenter and residential proxies, Custom geolocation in USA + 45 countries
Cloud Storage — Free$0/mo10k requests; 14 days retentionGet API, Delete API, Bulk API
Cloud Storage — Developer$29/mo100k requests; 30 days retentionGet API, Delete API, Bulk API
Cloud Storage — Business$249/mo1M requests; 30 days retentionGet API, Delete API, Bulk API
Cloud Storage — EnterpriseContact usCustom volume and retentionGet API, Delete API, Bulk API

Checked 2026-08-06 against their pricing page. Vendors change pricing without notice.

What is Crawlbase

Vendor's own claim

Crawlbase is an API-led web-data infrastructure product. The material retrieved here presents separate usage-based crawl products and subscription-based proxy and storage products; it is not only an agent connector or a simple proxy list.

Ideal customer profile

Our read

Engineering and data teams that need production web collection, want to avoid operating browser, proxy, retry, and anti-bot infrastructure themselves, and can integrate a token-authenticated API into a workflow.

Who should look elsewhere

Our read

It is a poor fit for a nontechnical GTM team looking for a ready-made prospect database: Crawlbase sells crawling infrastructure, and its own pricing FAQ says the Crawling API needs development knowledge or someone who can help. It is also overkill for simple static pages that do not need rendering, proxies, retry handling, or an agent integration.

Tools in the same layer

Our read

No curated rival set covers this tool yet, so these are simply other tools in the same architectural layer and product form. Treat it as a starting point, not a shortlist.

Crawlbase FAQ

Can an AI agent use Crawlbase through MCP?

Yes. The Web MCP Server documentation names three tools - crawl, crawl_markdown, and crawl_screenshot - and says it works with Claude Desktop, Cursor, Windsurf, n8n, and other MCP-compatible clients.

From official docs
What does the MCP server cost?

Crawlbase says the MCP server itself is free; requests it makes are billed through the Crawling API. The pricing material says up to 20,000 requests are free without a credit card.

From official docs
Can I use a stable IP instead of rotating every request?

The pricing FAQ says Crawling API requests receive a new IP by default and directs users who need a stable IP to sessions documented in the Crawling API docs.

From official docs

Verify before you buy

  • A machine-readable OpenAPI specification was not retrieved in this pass.
  • A confirmed API-reference URL, changelog, integrations page, help center, and separate developer-documentation host were not retrieved in this pass.
  • Exact Crawling API per-request price figures were rendered as an interactive calculator rather than retrieved as a fixed price table.
  • A machine-readable OpenAPI specification was not included in the reviewed source set.

Need help setting it up?

This page tells you whether Crawlbase fits. Cheetah builds and runs the system it goes into — enrichment, sequencing, CRM and the joins between them.

Book a call →

The directory stays free. There is nothing gated behind this.