molmim_decode · MolMIM MCP Server MCP: Risk & Policy

WHAT IT DOES

What molmim_decode does on MolMIM MCP Server

AI agents invoke molmim_decode to trigger actions in MolMIM MCP Server. 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 molmim_decode needs a policy

This tool runs a computational operation (decoding hidden states) against an external API. It neither reads stored data nor writes/modifies persistent data — it executes a transformation process. The blast radius is low as it only produces molecular string outputs with no side effects on data or systems.

From the tool's definition 'Decode hidden states back to SMILES strings. Converts MolMIM' — triggers a computational transformation via the NVIDIA MolMIM API, converting internal representations to molecular SMILES strings

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

molmim_decode Rate-limited

molmim_decode 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": {
    "molmim_decode": {
      "limits": [
        {
          "counter": "molmim_decode_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 MolMIM MCP Server, so you can run agents against it safely.

FAQ

Questions about molmim_decode

What does the molmim_decode tool do? +

Decode hidden states back to SMILES strings. Converts MolMIM. It is categorised as a Execute tool in the MolMIM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on molmim_decode? +

Register the MolMIM MCP Server MCP server in PolicyLayer and add a rule for molmim_decode: 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 MolMIM MCP Server. Nothing to install.

What risk level is molmim_decode? +

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

Can I rate-limit molmim_decode? +

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

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

molmim_decode is provided by the MolMIM MCP Server MCP server (siarhei-fedziukovich/mcp-molmim). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.