bindcraft_submit · BindCraft MCP: Risk & Policy

WHAT IT DOES

What bindcraft_submit does on BindCraft MCP

AI agents invoke bindcraft_submit to trigger actions in BindCraft 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 bindcraft_submit needs a policy

The tool name 'submit' strongly implies triggering a computational job execution (likely submitting a binder design job via Docker). Given the server context involves running structure prediction and sequence optimization pipelines, this is an Execute-category action. Severity is high because submitting compute jobs could consume significant resources or trigger long-running external operations.

From the tool's definition Tool name 'bindcraft_submit' on a server for 'protein binder design using BindCraft via Docker, enabling structure prediction, sequence optimization, and scoring'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bindcraft_submit Rate-limited

bindcraft_submit 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": {
    "bindcraft_submit": {
      "limits": [
        {
          "counter": "bindcraft_submit_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 BindCraft MCP, so you can run agents against it safely.

FAQ

Questions about bindcraft_submit

What does the bindcraft_submit tool do? +

bindcraft_submit. It is categorised as a Execute tool in the BindCraft 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 bindcraft_submit? +

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

What risk level is bindcraft_submit? +

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

Can I rate-limit bindcraft_submit? +

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

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

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