run_powershell
Run a local PowerShell command and return stdout/stderr.
This record as markdown: /tools/mcp-control-plane/run-powershell.md
What run_powershell does on Mcp Control Plane
AI agents invoke run_powershell to trigger actions in Mcp Control Plane. 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 run_powershell is rated High
PowerShell command execution is a broad Execute capability that permits running any command with the privileges of the process, including system modifications, file operations, network requests, data exfiltration, and lateral movement. The lack of documented restrictions or sandboxing means an AI agent could misuse this to cause severe, wide-ranging harm.
From the tool's definition Tool is named 'run_powershell' and described as 'Run a local PowerShell command and return stdout/stderr.' This directly executes arbitrary PowerShell commands on the local system.
Attacks that exploit this kind of access
The rule that runs run_powershell safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Control Plane, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_powershell, this is the rule to start with:
run_powershell 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Control Plane, apply this rule, and every run_powershell call is checked against it from then on.
Questions about run_powershell
Run a local PowerShell command and return stdout/stderr. It is categorised as a Execute tool in the Mcp Control Plane MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Control Plane MCP server in PolicyLayer and add a rule for run_powershell: 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 Mcp Control Plane. Nothing to install.
run_powershell 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_powershell 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_powershell. 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_powershell is provided by the Mcp Control Plane MCP server (albertik322-sudo/mcp-control-plane). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Control Plane, and thousands of servers like it.
Across the catalogue