Round duration in seconds for a timeframe.
AI agents call updown_tf_duration to retrieve information from Basis MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to return a computed or queried duration value (in seconds) for a given timeframe. This is a read/query operation with no financial, destructive, or write implications. Confidence is moderate because the description is minimal and the broader server context involves financial operations, but the tool itself seems purely informational.
From the tool's definition 'Round duration in seconds for a timeframe' — retrieves/computes a duration value, no side effects implied
Attacks that exploit this kind of access
Round duration in seconds for a timeframe. It is categorised as a Read tool in the Basis MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Basis MCP Server MCP server in PolicyLayer and add a rule for updown_tf_duration: 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 Basis MCP Server. Nothing to install.
updown_tf_duration 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 updown_tf_duration 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 updown_tf_duration. 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.
updown_tf_duration is provided by the Basis MCP Server MCP server (launch-on-basis/mcp-ts). 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 →