Wait for a human approval to resolve. Use after sidclaw_evaluate returns
AI agents call sidclaw_approve as a supporting operation in Sdk workflows.
This tool acts as a synchronization/gate mechanism in a human-in-the-loop approval workflow. It does not perform any data operation on its own — it simply blocks until a human approves or rejects. The closest category is 'Other' since it is a control-flow primitive.
From the tool's definition 'Wait for a human approval to resolve' — the tool pauses execution pending a human decision; it does not itself read, write, execute, destroy, or move money
Documented attack patterns abuse exactly the kind of access sidclaw_approve 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_approve:
{
"version": "1",
"default": "deny",
"tools": {
"sidclaw_approve": {
"limits": [
{
"counter": "sidclaw_approve_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
} sidclaw_approve gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Wait for a human approval to resolve. Use after sidclaw_evaluate returns. It is categorised as a Other tool in the Sdk MCP Server, which means it performs auxiliary operations.
Register the Sdk MCP server in PolicyLayer and add a rule for sidclaw_approve: 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_approve is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sidclaw_approve 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_approve. 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_approve 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.