AI agents call render_carbon_table to retrieve information from Maximo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a rendering/formatting tool that operates on already-retrieved Maximo data to generate visual HTML output. It has no side effects on data, does not query or fetch data itself, and does not execute operations or modify state. The only action is transforming data for display purposes, which falls under Read category with low severity.
From the tool's definition The tool 'render_carbon_table' takes Maximo data as input and 'Generates a beautiful Carbon Design System HTML table' - it transforms and presents existing data in HTML format without modifying, executing operations, or deleting anything.
Attacks that exploit this kind of access
Generates a beautiful Carbon Design System HTML table from Maximo data. It is categorised as a Read tool in the Maximo MCP Server, which means it retrieves data without modifying state.
Register the Maximo MCP server in PolicyLayer and add a rule for render_carbon_table: 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 Maximo. Nothing to install.
render_carbon_table 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 render_carbon_table 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 render_carbon_table. 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.
render_carbon_table is provided by the Maximo MCP server (maximo-mcp-server). 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 →