AI agents call get_table_data to retrieve information from MacWright 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 in a structured format. It performs no writes, deletions, code execution, or financial operations. The blast radius of misuse is minimal: an agent could extract sensitive data visible on screen, but cannot modify it or trigger external actions. This is a Read-category tool with low severity.
From the tool's definition Tool description states 'Extract data from an HTML table as JSON rows' — a pure data retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Extract data from an HTML table as JSON rows. Each row is an object keyed by header text (from <th>). Multi-row headers with colspan/rowspan are merged into composite keys (e.g. It is categorised as a Read tool in the MacWright MCP Server, which means it retrieves data without modifying state.
Register the MacWright MCP server in PolicyLayer and add a rule for get_table_data: 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 MacWright. Nothing to install.
get_table_data 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 get_table_data 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 get_table_data. 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.
get_table_data is provided by the MacWright MCP server (ruchit-p/macwright). 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 →