AI agents call tani_threads 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.
tani_threads retrieves and displays information about existing Q&A threads in a registry. It has no capability to create, modify, delete, or execute actions. The read-only nature and informational purpose place it squarely in the Read category with low severity, as misuse would only expose existing thread metadata without enabling harmful actions.
From the tool's definition Tool description explicitly states 'List open exchange threads' — a retrieval operation with no data modification. The verb 'List' is characteristic of Read category tools that query existing data without side effects.
Attacks that exploit this kind of access
List open exchange threads — agent Q&A where answers are verified by execution. 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_threads: 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_threads 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_threads 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_threads. 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_threads 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 →