Scrape content from a single URL with advanced options. **Best for:** Single page content extraction, when you know exactly which page contains the information. **Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract). **Common mistake...
Accepts URL/endpoint input (url); Accepts freeform code/query input (actions[].script); High parameter count (26 properties); Single-target operation
Part of the Firecrawl Web Scraping Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call firecrawl_scrape to retrieve information from Firecrawl Web Scraping Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though firecrawl_scrape only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
firecrawl_scrape:
rules:
- action: allowSee the full Firecrawl Web Scraping Server policy for all 8 tools.
Agents calling read-class tools like firecrawl_scrape have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Scrape content from a single URL with advanced options. **Best for:** Single page content extraction, when you know exactly which page contains the information. **Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract). **Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). **Prompt Example:** "Get the content of the page at https://example.com." **Usage Example:** ```json { "name": "firecrawl_scrape", "arguments": { "url": "https://example.com", "formats": ["markdown"] } } ``` **Returns:** Markdown, HTML, or other formats as specified. . It is categorised as a Read tool in the Firecrawl Web Scraping Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for firecrawl_scrape. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Firecrawl Web Scraping Server MCP server.
firecrawl_scrape 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 firecrawl_scrape rule in your Intercept 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 Intercept policy for firecrawl_scrape. 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.
firecrawl_scrape is provided by the Firecrawl Web Scraping Server MCP server (NYO2008/firecrawl-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept