Extract text content from a public URL (SSRF-protected)
AI agents call web_extract to retrieve information from Mcp Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries content from URLs without modifying or deleting data. It falls squarely into the Read category. Severity is medium rather than low because SSRF vulnerabilities (even if mitigated) and unfiltered web content extraction could expose sensitive information or be weaponized for reconnaissance if an agent is compromised or misdirected.
From the tool's definition Tool name 'web_extract' and description 'Extract text content from a public URL' indicate retrieval of data with no side effects. SSRF protection confirms safety boundaries.
Attacks that exploit this kind of access
Extract text content from a public URL (SSRF-protected). It is categorised as a Read tool in the Mcp Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Mcp Toolkit MCP server in PolicyLayer and add a rule for web_extract: 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 Mcp Toolkit. Nothing to install.
web_extract 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 web_extract 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 web_extract. 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.
web_extract is provided by the Mcp Toolkit MCP server (studiopig/mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →