create_workspace · Persistent Shell MCP: Risk & Policy

WHAT IT DOES

What create_workspace does on Persistent Shell MCP

AI agents invoke create_workspace to trigger actions in Persistent Shell 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.

WHY IT NEEDS A POLICY

Why create_workspace needs a policy

Creating a workspace initializes a persistent tmux session environment that is specifically designed to execute shell commands and manage processes. While workspace creation itself is closer to a Write action, in the context of this server it provisions an execution environment (tmux session) that enables subsequent shell command execution.

From the tool's definition 'Create a new isolated workspace for commands' within a server that 'enables AI assistants to execute shell commands and manage long-running processes within persistent tmux sessions'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_workspace Rate-limited

create_workspace 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": {
    "create_workspace": {
      "limits": [
        {
          "counter": "create_workspace_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 Persistent Shell MCP, so you can run agents against it safely.

FAQ

Questions about create_workspace

What does the create_workspace tool do? +

Create a new isolated workspace for commands. It is categorised as a Execute tool in the Persistent Shell MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_workspace? +

Register the Persistent Shell MCP server in PolicyLayer and add a rule for create_workspace: 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 Persistent Shell MCP. Nothing to install.

What risk level is create_workspace? +

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

Can I rate-limit create_workspace? +

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

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

create_workspace is provided by the Persistent Shell MCP server (tntisdial/persistent-shell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.