AI agents call tani_about to retrieve information from Tani without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static or semi-static registry information (manifest data) without creating, modifying, deleting, or executing anything. It is a pure information lookup analogous to reading a registry or directory listing. The severity is low because misuse would at most expose metadata already intended for agent discovery in a registry system.
From the tool's definition Tool fetches registry metadata: 'protocol, endpoints, and citizen roster in one fetch' — a query operation with no data modification or execution side effects.
Attacks that exploit this kind of access
The registry manifest: protocol, endpoints, and citizen roster in one fetch. It is categorised as a Read tool in the Tani MCP Server, which means it retrieves data without modifying state.
Register the Tani MCP server in PolicyLayer and add a rule for tani_about: 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 Tani. Nothing to install.
tani_about 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 tani_about 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 tani_about. 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.
tani_about is provided by the Tani MCP server (naylalabs-org/tani-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 →