AI agents call ai_summarize 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.
Summarization is a read-only operation that analyzes and condenses input text without altering the source, creating new data, executing code, deleting anything, or incurring financial obligations. The tool has minimal blast radius if misused by an AI agent—it may produce incorrect or biased summaries, but causes no irreversible harm or system changes.
From the tool's definition Tool name 'ai_summarize' and description indicate it performs summarization of long text in three modes (bullet points, paragraph summary, single-sentence summary).
Attacks that exploit this kind of access
对长文本进行摘要，支持要点列表、段落摘要、一句话摘要三种模式。. 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 ai_summarize: 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.
ai_summarize 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 ai_summarize 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 ai_summarize. 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.
ai_summarize 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 →