boltzgen_run · BoltzGen MCP: Risk & Policy

WHAT IT DOES

What boltzgen_run does on BoltzGen MCP

AI agents invoke boltzgen_run to trigger actions in BoltzGen 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 boltzgen_run needs a policy

This tool triggers execution of potentially resource-intensive GPU-based protein design operations. Misuse could exhaust computational resources, generate malicious protein structures, or be weaponized for harmful biological design.

From the tool's definition Tool name 'boltzgen_run' combined with server context describing 'GPU-accelerated Docker deployment and async job management' and sibling tools like 'boltzgen_submit' and 'boltzgen_cancel_job' indicate this runs computational jobs.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

boltzgen_run Rate-limited

boltzgen_run 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": {
    "boltzgen_run": {
      "limits": [
        {
          "counter": "boltzgen_run_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 BoltzGen MCP, so you can run agents against it safely.

FAQ

Questions about boltzgen_run

What does the boltzgen_run tool do? +

boltzgen_run. It is categorised as a Execute tool in the BoltzGen 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 boltzgen_run? +

Register the BoltzGen MCP server in PolicyLayer and add a rule for boltzgen_run: 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 BoltzGen MCP. Nothing to install.

What risk level is boltzgen_run? +

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

Can I rate-limit boltzgen_run? +

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

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

boltzgen_run is provided by the BoltzGen MCP server (macromnex/boltzgen_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.