fit_uncertainty_model · Pybme MCP: Risk & Policy

WHAT IT DOES

What fit_uncertainty_model does on Pybme

AI agents invoke fit_uncertainty_model 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.

WHY IT NEEDS A POLICY

Why fit_uncertainty_model needs a policy

Fitting an uncertainty model involves running a computational algorithm (Bayesian Maximum Entropy geostatistical fitting) which constitutes execution of a non-trivial process. The registration aspect also writes state. Since execution of the modeling process is the primary action, Execute is the most appropriate category.

From the tool's definition 'Fit or register an uncertainty model' — fitting a model executes a computational process (model training/optimization) and registering it creates or modifies state in the modeling context

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fit_uncertainty_model Rate-limited

fit_uncertainty_model stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "fit_uncertainty_model": {
      "limits": [
        {
          "counter": "fit_uncertainty_model_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Pybme, so you can run agents against it safely.

FAQ

Questions about fit_uncertainty_model

What does the fit_uncertainty_model tool do? +

Fit or register an uncertainty model at the level of scientific intent rather than low-level API calls. 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.

How do I enforce a policy on fit_uncertainty_model? +

Register the Pybme MCP server in PolicyLayer and add a rule for fit_uncertainty_model: 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.

What risk level is fit_uncertainty_model? +

fit_uncertainty_model is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit fit_uncertainty_model? +

Yes. Add a rate_limit block to the fit_uncertainty_model 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.

How do I block fit_uncertainty_model completely? +

Set action: deny in the PolicyLayer policy for fit_uncertainty_model. 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.

What MCP server provides fit_uncertainty_model? +

fit_uncertainty_model 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.