ingest_external_scenario_evidence · Pybme MCP: Risk & Policy

WHAT IT DOES

What ingest_external_scenario_evidence does on Pybme

AI agents use ingest_external_scenario_evidence to create or update resources in Pybme — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pybme environment.

WHY IT NEEDS A POLICY

Why ingest_external_scenario_evidence needs a policy

This tool creates and modifies data (ingests evidence into a bundle) in a reversible manner. While it imports external data, the core action is writing/storing that data into the system's modeling context. This is a Write operation rather than Read (it doesn't just query existing evidence) or Execute (it doesn't run arbitrary code or trigger unpredictable external operations).

From the tool's definition Tool description states it will 'Ingest externally produced evidence... into a reusable bundle' and make it referenceable 'by evidence_id', indicating creation and storage of new data structures.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ingest_external_scenario_evidence Rate-limited

ingest_external_scenario_evidence stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ingest_external_scenario_evidence": {
      "limits": [
        {
          "counter": "ingest_external_scenario_evidence_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 ingest_external_scenario_evidence

What does the ingest_external_scenario_evidence tool do? +

Ingest externally produced evidence (hard data, soft PDFs, network topology) into a reusable bundle. Subsequent fit and update tools can reference the bundle by evidence_id. It is categorised as a Write tool in the Pybme MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ingest_external_scenario_evidence? +

Register the Pybme MCP server in PolicyLayer and add a rule for ingest_external_scenario_evidence: 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 ingest_external_scenario_evidence? +

ingest_external_scenario_evidence is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit ingest_external_scenario_evidence? +

Yes. Add a rate_limit block to the ingest_external_scenario_evidence 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 ingest_external_scenario_evidence completely? +

Set action: deny in the PolicyLayer policy for ingest_external_scenario_evidence. 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 ingest_external_scenario_evidence? +

ingest_external_scenario_evidence 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.