Pre-action policy check. Call before executing any risky action.
AI agents call sidclaw_evaluate to retrieve information from Sdk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a policy evaluation query before an action is taken. It reads/checks policy rules and returns a decision (approve/deny), but does not itself execute any action, modify data, or trigger external operations. Similar to a read/query against a policy engine.
From the tool's definition 'Pre-action policy check. Call before executing any risky action.' — this is an evaluation/check step, not execution of the risky action itself.
Documented attack patterns abuse exactly the kind of access sidclaw_evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sdk, and nothing reaches the server without passing your rules. This is the rule we recommend for sidclaw_evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"sidclaw_evaluate": {}
}
}sidclaw_evaluate is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Pre-action policy check. Call before executing any risky action. It is categorised as a Read tool in the Sdk MCP Server, which means it retrieves data without modifying state.
Register the Sdk MCP server in PolicyLayer and add a rule for sidclaw_evaluate: 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 Sdk. Nothing to install.
sidclaw_evaluate is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sidclaw_evaluate 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.
Set action: deny in the PolicyLayer policy for sidclaw_evaluate. 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.
sidclaw_evaluate is provided by the Sdk MCP server (@sidclaw/sdk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sdk, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Sdk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.