evaluate_rules · Sablier MCP Server MCP: Risk & Policy

WHAT IT DOES

What evaluate_rules does on Sablier MCP Server

AI agents invoke evaluate_rules to trigger actions in Sablier 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 evaluate_rules needs a policy

The description is empty, which significantly lowers confidence. Based on the tool name 'evaluate_rules' and the context of sibling tools like 'backtest_rules', this likely executes rule logic against portfolio or market data. 'Evaluate' implies computation/execution rather than simple data retrieval or modification. Without more detail, Execute is the most plausible category, but confidence is low.

From the tool's definition Tool name 'evaluate_rules' with empty description; sibling tools include 'backtest_rules' and 'analyze_*' functions suggesting rule evaluation/execution logic

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_rules Rate-limited

evaluate_rules 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": {
    "evaluate_rules": {
      "limits": [
        {
          "counter": "evaluate_rules_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 Sablier MCP Server, so you can run agents against it safely.

FAQ

Questions about evaluate_rules

What does the evaluate_rules tool do? +

evaluate_rules. It is categorised as a Execute tool in the Sablier 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 evaluate_rules? +

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

What risk level is evaluate_rules? +

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

Can I rate-limit evaluate_rules? +

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

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

evaluate_rules is provided by the Sablier MCP Server MCP server (sablier-ai/sablier-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.