AI agents call sys_hash 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.
Hashing is a one-way computational function that takes input data and produces a fixed-size output. It does not create, modify, delete, execute external operations, or involve financial transactions. It purely reads the input string/text and returns a computed hash value, making it a Read category tool with low severity and blast radius.
From the tool's definition Tool name 'sys_hash' and description '计算字符串或文本的哈希值' (compute hash value of string or text) indicate a cryptographic operation that reads input and produces a deterministic output without modifying data or triggering side effects.
Attacks that exploit this kind of access
计算字符串或文本的哈希值。. 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 sys_hash: 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.
sys_hash 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 sys_hash 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 sys_hash. 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.
sys_hash 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 →