AI agents call data_table_format to retrieve information from Onion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data formatting utility that reads JSON array input and produces a text representation (Markdown table). It has no side effects, does not modify or delete the source data, does not execute arbitrary code or system commands, and does not involve financial operations. It is a pure read/transform operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name and description indicate formatting/transformation of data: '将 JSON 数组数据格式化为 Markdown 表格' translates to 'Format JSON array data as Markdown table'.
Attacks that exploit this kind of access
将 JSON 数组数据格式化为 Markdown 表格。. It is categorised as a Read tool in the Onion MCP Server, which means it retrieves data without modifying state.
Register the Onion MCP server in PolicyLayer and add a rule for data_table_format: 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 Onion. Nothing to install.
data_table_format 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 data_table_format 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 data_table_format. 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.
data_table_format is provided by the Onion MCP server (onion-ai/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 →