AI agents call dev.uuid to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
UUID generation is a read-like operation: it queries a computational function and returns data without creating, modifying, or deleting any persistent state. The tool does not execute arbitrary code, destroy data, or involve financial transactions. The cryptographic randomness is internal to the computation and does not affect the classification.
From the tool's definition Tool description states it "Generate[s] UUIDs" with "Pure compute, no upstream" — a deterministic computation that retrieves/outputs data with no side effects on persistent state.
Attacks that exploit this kind of access
Generate UUIDs. version v4 (random) or v7 (time-ordered, sortable); count 1-100. Cryptographically random. Pure compute, no upstream. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for dev.uuid: 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 Mcp. Nothing to install.
dev.uuid 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 dev.uuid 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 dev.uuid. 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.
dev.uuid is provided by the MCP server (@2sio/mcp). 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 →