crawl4ai-mcp-server

Provides an MCP (Model Context Protocol) server that exposes Crawl4AI web scraping/crawling capabilities (scrape, crawl, URL discovery, search, extract) to MCP clients such as Claude Desktop. It is intended to run as a remote service on Cloudflare Workers and supports OAuth and Bearer-token (API key) authentication.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Infrastructure mcp web-scraping crawling oauth cloudflare-workers typescript ai-assistants
⚙ Agent Friendliness
44
/ 100
Can an agent use this?
🔒 Security
55
/ 100
Is it safe for agents?
⚡ Reliability
24
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
45
Error Messages
0
Auth Simplicity
55
Rate Limits
10

🔒 Security

TLS Enforcement
80
Auth Strength
65
Scope Granularity
25
Dep. Hygiene
45
Secret Handling
55

Supports OAuth and Bearer tokens per README; however, there is no documented authorization model (scopes/permissions), no documented token handling/rotation, and no explicit security headers/logging guidance shown. Runs on Cloudflare Workers and uses KV, which may store crawl data; data retention/access controls are not described.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
40
Error Recovery
20
AF Security Reliability

Best When

You want an MCP-tooling integration to trigger Crawl4AI workflows from an AI assistant and can tolerate early-stage reliability for development/testing.

Avoid When

You need strict SLA/uptime guarantees, mature error semantics, or you cannot provide OAuth/Bearer authentication configuration.

Use Cases

  • Letting AI assistants scrape or crawl web content via MCP tools
  • Performing structured content extraction from URLs (CSS-selector or LLM-assisted extraction as supported by Crawl4AI)
  • Crawling a site and then searching indexed crawl results
  • Automating research workflows that require multi-page web acquisition

Not For

  • Production use (repo README explicitly states MCP server is under development / not ready for production)
  • Use cases requiring guaranteed scraping correctness/robustness on all sites (no guarantees documented)
  • Environments needing a standard REST/GraphQL/OpenAPI API without MCP

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: OAuth (workers-oauth-provider) Bearer token (API key) authentication
OAuth: Yes Scopes: No

README mentions OAuth and API key/Bearer token options but does not document scopes/authorization granularity or token lifecycle/rotation details.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; deployed on Cloudflare Workers likely implies usage-based infrastructure costs, but not specified.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Server is explicitly marked as under development / not production ready; tool reliability may be inconsistent.
  • No documented rate-limit behavior or retry/idempotency semantics for MCP tools in README.
  • Cloudflare Workers deployment and KV configuration are required for some stateful behaviors (e.g., crawl data), which may impact local testing and agent environments.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for crawl4ai-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered