Extract tables from a page and return as markdown tables.
AI agents call web_fetch_tables to retrieve information from Smart Webfetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves tabular data from web pages, converting it to markdown format for display. It performs no writes, deletions, code execution, or financial operations. The worst-case misuse scenario (fetching sensitive tables) has limited blast radius compared to write/execute/destructive operations. Confidence is high due to explicit 'extract' language in the description.
From the tool's definition Tool name 'web_fetch_tables' and description 'Extract tables from a page and return as markdown tables' indicate data retrieval with no modifications or side effects.
Attacks that exploit this kind of access
Extract tables from a page and return as markdown tables. It is categorised as a Read tool in the Smart Webfetch MCP Server, which means it retrieves data without modifying state.
Register the Smart Webfetch MCP server in PolicyLayer and add a rule for web_fetch_tables: 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 Smart Webfetch. Nothing to install.
web_fetch_tables 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_fetch_tables 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_fetch_tables. 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_fetch_tables is provided by the Smart Webfetch MCP server (mathisto/smart-webfetch-mcp). 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 →