AI agents invoke run_uncertainty_update to trigger actions in Pybme. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool triggers a geostatistical computation that updates internal model state and produces new inference results. While not destructive (reversible) or creating persistent data artifacts (Write), it executes a non-trivial algorithm whose outputs depend on argument values. An agent misusing this with adversarial evidence could produce misleading uncertainty estimates affecting downstream decisions.
From the tool's definition The tool 'run_uncertainty_update' performs an active computational operation that 'assimilates' evidence into a posterior scenario using a fitted model. This is an execution action that transforms state based on inputs (evidence and model parameters).
Attacks that exploit this kind of access
Assimilate hard and soft evidence into a posterior scenario using a previously fitted uncertainty model. It is categorised as a Execute tool in the Pybme MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pybme MCP server in PolicyLayer and add a rule for run_uncertainty_update: 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.
run_uncertainty_update is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_uncertainty_update 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 run_uncertainty_update. 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.
run_uncertainty_update 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.
run_uncertainty_update is one line of Pybme's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →