Issue a delegated capability token to a sub-agent with narrower scope than the current token. Use this when one agent should perform a bounded sub-task without inheriting full access. The delegated token is always attenuated (depth = parent.depth + 1; max depth 3). Returns a JSON object containin...
AI agents use sint__delegate_to_agent to create or update resources in SINT Protocol — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SINT Protocol environment.
This tool creates a new capability token granting access permissions to a sub-agent. While it is attenuated (narrower scope), it is a Write operation that provisions access credentials. Misuse could allow an AI agent to delegate capabilities to untrusted sub-agents, expanding the attack surface even within stated constraints.
From the tool's definition Issue a delegated capability token to a sub-agent with narrower scope than the current token
Documented attack patterns abuse exactly the kind of access sint__delegate_to_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SINT Protocol, and nothing reaches the server without passing your rules. This is the rule we recommend for sint__delegate_to_agent:
{
"version": "1",
"default": "deny",
"tools": {
"sint__delegate_to_agent": {
"limits": [
{
"counter": "sint__delegate_to_agent_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}sint__delegate_to_agent 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.
Free to start. No card required.
Issue a delegated capability token to a sub-agent with narrower scope than the current token. Use this when one agent should perform a bounded sub-task without inheriting full access. The delegated token is always attenuated (depth = parent.depth + 1; max depth 3). Returns a JSON object containing the new token ID, delegated scope, depth, and expiry. It is categorised as a Write tool in the SINT Protocol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SINT Protocol MCP server in PolicyLayer and add a rule for sint__delegate_to_agent: 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 SINT Protocol. Nothing to install.
sint__delegate_to_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the sint__delegate_to_agent 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 sint__delegate_to_agent. 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.
sint__delegate_to_agent is provided by the SINT Protocol MCP server (sint-ai/sint-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SINT Protocol, 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.
21 SINT Protocol tools catalogued and risk-classified — across an index of 43,000+ MCP servers.