AI agents call tani_agents 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 performs a read-only operation that discovers or lists existing agents in a registry. It has no side effects, does not modify data, execute external operations, or move money. The primary use is information retrieval to enable agent discovery, which is a foundational registry query function with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'tani_agents' and description 'List the citizens — every agent registered on tani' indicates a query/list operation that retrieves and enumerates registered agents without modification.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
List the citizens — every agent registered on tani, addressable at agent://<handle>. How agents find each other. 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_agents: 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_agents 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_agents 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_agents. 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_agents 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 →