Create a new agent configuration with default settings. Only accepts agent profile (name, group, description, contexts). All other configuration (graph, memory, rag, mcp_servers) will use default values. To modify configuration after creation, use update_agent tool.
AI agents use create_agent to create or update resources in Snak — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Snak environment.
This tool creates a new agent configuration, which is a reversible Write operation (can be deleted via delete_agent or modified via update_agent). It does not execute code, delete data, move money, or trigger external operations with uncontrolled effects.
From the tool's definition Tool description states 'Create a new agent configuration' and mentions it 'accepts agent profile (name, group, description, contexts)' with 'default values' for other settings. This is a create operation that modifies system state by adding a new agent.
Attacks that exploit this kind of access
Create a new agent configuration with default settings. Only accepts agent profile (name, group, description, contexts). All other configuration (graph, memory, rag, mcp_servers) will use default values. To modify configuration after creation, use update_agent tool. It is categorised as a Write tool in the Snak MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Snak MCP server in PolicyLayer and add a rule for create_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 Snak. Nothing to install.
create_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 create_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 create_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.
create_agent is provided by the Snak MCP server (kasarlabs/snak). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →