start-interaction | PolicyLayer

WHAT IT DOES

What start-interaction does on RSK MCP Server - Rootstock Blockchain Tools

AI agents invoke start-interaction to trigger actions in RSK MCP Server - Rootstock Blockchain Tools. 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 start-interaction needs a policy

This tool initiates CLI-based execution of blockchain operations. While the tool itself is a gateway/entry point, it provides access to Execute-category functions (wallet management, transfers, contract deployment) whose outcomes depend on how an agent uses them. The financial implications (token transfers) and irreversible nature (smart contract deployment) are mediated through this execution interface.

From the tool's definition Tool description states it 'Start interaction with the Rootstock CLI functions' - CLI interaction is code execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start-interaction Rate-limited

start-interaction 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": {
    "start-interaction": {
      "limits": [
        {
          "counter": "start-interaction_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 RSK MCP Server - Rootstock Blockchain Tools, so you can run agents against it safely.

FAQ

Questions about start-interaction

What does the start-interaction tool do? +

Start interaction with the Rootstock CLI functions, start this once someone ask something related to the rootstock (rsk) blockchain. It is categorised as a Execute tool in the RSK MCP Server - Rootstock Blockchain Tools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start-interaction? +

Register the RSK MCP Server - Rootstock Blockchain Tools MCP server in PolicyLayer and add a rule for start-interaction: 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 RSK MCP Server - Rootstock Blockchain Tools. Nothing to install.

What risk level is start-interaction? +

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

Can I rate-limit start-interaction? +

Yes. Add a rate_limit block to the start-interaction 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 start-interaction completely? +

Set action: deny in the PolicyLayer policy for start-interaction. 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 start-interaction? +

start-interaction is provided by the RSK MCP Server - Rootstock Blockchain Tools MCP server (rsksmart/rsk-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.