run_remote_script · Tacc Mcp Bio MCP: Risk & Policy

WHAT IT DOES

What run_remote_script does on Tacc Mcp Bio

AI agents invoke run_remote_script to trigger actions in Tacc Mcp Bio. 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 run_remote_script needs a policy

This tool executes code on a remote TACC/SLURM HPC cluster. The effects are determined by the script content and cannot be easily predicted or reverted. It poses significant risk if an AI agent is manipulated into running malicious or destructive scripts (e.g., data deletion, resource exhaustion, lateral movement).

From the tool's definition Tool name 'run_remote_script' indicates execution of arbitrary scripts on a remote HPC cluster. Server description explicitly mentions 'remote script execution' as a capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_remote_script Rate-limited

run_remote_script 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": {
    "run_remote_script": {
      "limits": [
        {
          "counter": "run_remote_script_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 Tacc Mcp Bio, so you can run agents against it safely.

FAQ

Questions about run_remote_script

What does the run_remote_script tool do? +

run_remote_script. It is categorised as a Execute tool in the Tacc Mcp Bio MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_remote_script? +

Register the Tacc Mcp Bio MCP server in PolicyLayer and add a rule for run_remote_script: 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 Tacc Mcp Bio. Nothing to install.

What risk level is run_remote_script? +

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

Can I rate-limit run_remote_script? +

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

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

run_remote_script is provided by the Tacc Mcp Bio MCP server (narasimhan-lab/tacc-mcp-bio). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.