Crawl a URL and extract clean markdown content. Pass store=true to persist the original page in Cloud Storage and return only the RID + metadata.
AI agents call crawl_markdown 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.
This tool retrieves web content and optionally stores it. Both actions are non-destructive and reversible. The core function is fetching and reading data (crawling), which is a Read operation. Storage is incidental to the retrieval, not a primary modification of existing application state. The blast radius of misuse is limited to unauthorized content access or storage of benign cached pages.
From the tool's definition Tool description states it 'crawl[s] a URL and extract[s] clean markdown content' and optionally 'persist[s] the original page in Cloud Storage' — these are retrieval and storage operations with no modification of existing data.
Documented attack patterns abuse exactly the kind of access crawl_markdown gives an agent:
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_markdown:
{
"version": "1",
"default": "deny",
"tools": {
"crawl_markdown": {}
}
}crawl_markdown is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Crawl a URL and extract clean markdown content. Pass store=true to persist the original page in Cloud Storage and return only the RID + metadata. It is categorised as a Read tool in the Crawlbase MCP MCP Server, which means it retrieves data without modifying state.
Register the Crawlbase MCP server in PolicyLayer and add a rule for crawl_markdown: 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.
crawl_markdown is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crawl_markdown 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.
Set action: deny in the PolicyLayer policy for crawl_markdown. 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.
crawl_markdown 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.
Start from Crawlbase MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Crawlbase MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.