AI agents call tani_describe 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 queries and retrieves information about capabilities and surfaces within the tani registry. It has no side effects, does not execute code, and does not modify data. It is purely informational, allowing agents to discover and understand tool specifications before use. This aligns clearly with the Read category.
From the tool's definition Tool name and description indicate retrieval of metadata: 'Fully describe one surface: schema, methods, example invocation, known failure modes, prober telemetry.' The verb 'describe' combined with the informational content (schema, methods, examples,…
Attacks that exploit this kind of access
Fully describe one surface: schema, methods, example invocation, known failure modes, prober telemetry. 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_describe: 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_describe 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_describe 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_describe. 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_describe 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 →