crawl_screenshot

Take a screenshot of a webpage. Pass store=true to persist the underlying HTML page to Cloud Storage (the screenshot itself is not stored and is still returned as an ephemeral screenshot_url).

ServerCrawlbase MCP
CategoryRead

How to control crawl_screenshot ↓

WHAT IT DOES

What crawl_screenshot does on Crawlbase MCP

AI agents call crawl_screenshot to retrieve information from Crawlbase MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

THE RISK

Low Risk

Why crawl_screenshot needs a policy

Screenshot capture is fundamentally a retrieval operation that queries and extracts visual data from a webpage without modifying the target resource. While the tool offers optional persistence to cloud storage (Write), the core capability is Read.

From the tool's definition The tool 'take a screenshot of a webpage' retrieves visual content from a live web page. The optional store=true parameter 'persist[s] the underlying HTML page to Cloud Storage', which is a Write operation on the storage system, but the primary…

Documented attack patterns abuse exactly the kind of access crawl_screenshot gives an agent:

POLICY

How to control crawl_screenshot

PolicyLayer is an MCP gateway — it sits between your AI agents and Crawlbase MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for crawl_screenshot:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "crawl_screenshot": {}
  }
}

crawl_screenshot is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Crawlbase MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Crawlbase MCP tools

Destructive storage_bulk_delete Bulk-delete up to 100 items from Crawlbase Cloud Storage by RID. Irreversible. Destructive storage_delete Delete a single item from Crawlbase Cloud Storage by RID. Read crawl Crawl a URL and return HTML content. Pass store=true to push the result to Crawlbase Cloud Read crawl_markdown Crawl a URL and extract clean markdown content. Pass store=true to persist the original pa Read storage_bulk_get Bulk-fetch up to 100 stored items by RID. Bodies are decoded automatically. Default as=met Read storage_count Get the total number of documents in Crawlbase Cloud Storage. Read storage_get Retrieve a single stored page from Crawlbase Cloud Storage by RID or URL. Only works for p Read storage_list List RIDs of pages previously crawled with store=true in Crawlbase Cloud Storage. Supports

All 9 Crawlbase MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about crawl_screenshot

What does the crawl_screenshot tool do? +

Take a screenshot of a webpage. Pass store=true to persist the underlying HTML page to Cloud Storage (the screenshot itself is not stored and is still returned as an ephemeral screenshot_url). It is categorised as a Read tool in the Crawlbase MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on crawl_screenshot? +

Register the Crawlbase MCP server in PolicyLayer and add a rule for crawl_screenshot: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crawlbase MCP. Nothing to install.

What risk level is crawl_screenshot? +

crawl_screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit crawl_screenshot? +

Yes. Add a rate_limit block to the crawl_screenshot rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block crawl_screenshot completely? +

Set action: deny in the PolicyLayer policy for crawl_screenshot. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides crawl_screenshot? +

crawl_screenshot is provided by the Crawlbase MCP server (crawlbase/crawlbase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Crawlbase MCP tool call.

Start from Crawlbase MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

9 Crawlbase MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.