[Deprecated] Run power flow. Use run_simulation(mode='pf') instead.
AI agents invoke run_powerflow to trigger actions in PyPSA MCP. 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.
Power flow analysis is a computational operation that executes algorithms on the energy system model to solve for voltages, currents, and power flows. While not destructive or modifying the underlying data permanently, it performs active computation whose effects are contingent on model parameters and arguments. This fits the Execute category as it triggers external computational operations.
From the tool's definition Tool description states 'Run power flow', which executes an energy system simulation on the model. Power flow analysis involves computational operations that transform the state of the network model and produce output results.
Documented attack patterns abuse exactly the kind of access run_powerflow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PyPSA MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_powerflow:
{
"version": "1",
"default": "deny",
"tools": {
"run_powerflow": {
"limits": [
{
"counter": "run_powerflow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_powerflow 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.
Free to start. No card required.
[Deprecated] Run power flow. Use run_simulation(mode='pf') instead. It is categorised as a Execute tool in the PyPSA MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PyPSA MCP server in PolicyLayer and add a rule for run_powerflow: 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 PyPSA MCP. Nothing to install.
run_powerflow 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_powerflow 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_powerflow. 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_powerflow is provided by the PyPSA MCP server (open-energy-transition/pypsa-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 PyPSA MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
22 PyPSA MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.