declare_capability · Moltmark MCP: Risk & Policy

WHAT IT DOES

What declare_capability does on Moltmark

AI agents use declare_capability to create or update resources in Moltmark — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moltmark environment.

WHY IT NEEDS A POLICY

Why declare_capability needs a policy

This tool creates new capability records in the PostgreSQL database for an agent. It is a write operation (creating/registering data) that could be misused to falsely attribute capabilities to an agent, potentially influencing trust scores and certification outcomes. It does not delete data or execute code, making Write the most appropriate category.

From the tool's definition 'Register a new skill or capability for an agent. This declares what the agent can do.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

declare_capability Rate-limited

declare_capability stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "declare_capability": {
      "limits": [
        {
          "counter": "declare_capability_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Moltmark, so you can run agents against it safely.

FAQ

Questions about declare_capability

What does the declare_capability tool do? +

Register a new skill or capability for an agent. This declares what the agent can do. It is categorised as a Write tool in the Moltmark MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on declare_capability? +

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

What risk level is declare_capability? +

declare_capability is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit declare_capability? +

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

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

declare_capability is provided by the Moltmark MCP server (moltobene-studio/mcp-server-moltmark). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.