AI agents call focus to retrieve information from TempoGraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without descriptive text, confidence is reduced. However, the naming pattern and context of sibling tools strongly indicate this is a read-only query or filtering operation. Most likely behavior: focuses or filters code graph results for analysis. No side effects, no code execution, no data modification.
From the tool's definition Tool name 'focus' with empty description suggests a viewer or navigator function typical of code graph tools.
Attacks that exploit this kind of access
focus. It is categorised as a Read tool in the TempoGraph MCP Server, which means it retrieves data without modifying state.
Register the TempoGraph MCP server in PolicyLayer and add a rule for focus: 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 TempoGraph. Nothing to install.
focus 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 focus 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 focus. 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.
focus is provided by the TempoGraph MCP server (tempograph). 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 →