AI agents call text_diff 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.
The tool performs text comparison and analysis, which is a retrieval and query operation with no side effects. It reads two inputs, processes them, and returns a formatted diff output. No data is created, modified, deleted, or executed as a result of using this tool. This is a classic Read category operation.
From the tool's definition Tool name 'text_diff' and description indicating it compares two text segments and outputs unified diff format. The Chinese description '对比两段文本的差异，输出 unified diff 格式' translates to 'compare the differences between two text segments, output unified diff format.
Attacks that exploit this kind of access
对比两段文本的差异，输出 unified diff 格式。. 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 text_diff: 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.
text_diff 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 text_diff 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 text_diff. 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.
text_diff 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 →