AI agents call explain_uncertainty_drivers to retrieve information from Pybme without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs analytical interpretation of Bayesian model results—specifically explaining uncertainty sources and inference changes. It is a read-only introspection operation that queries the model's internal state and posterior distribution to provide explanatory output. There is no data modification, execution of external commands, deletion, or financial impact.
From the tool's definition Tool name 'explain_uncertainty_drivers' and description 'Explain what is driving posterior uncertainty and how new evidence changed the inference state' indicate the tool retrieves and analyzes existing model state and uncertainty information without…
Attacks that exploit this kind of access
Explain what is driving posterior uncertainty and how new evidence changed the inference state. It is categorised as a Read tool in the Pybme MCP Server, which means it retrieves data without modifying state.
Register the Pybme MCP server in PolicyLayer and add a rule for explain_uncertainty_drivers: 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 Pybme. Nothing to install.
explain_uncertainty_drivers 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 explain_uncertainty_drivers 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 explain_uncertainty_drivers. 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.
explain_uncertainty_drivers is provided by the Pybme MCP server (wiesnerfriedman/pybme-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 →