AI agents use create_agent to create or update resources in AnythingLLM MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AnythingLLM MCP Server environment.
This tool creates a new AI agent configuration, which is a reversible write operation. While AI agents can have significant capabilities depending on their configuration, the act of creation itself is a Write operation. Severity is medium because improperly configured agents could perform unintended actions, but the creation is reversible (there is a sibling 'delete_agent' tool).
From the tool's definition 'Create a new agent' — creates a new resource (an AI agent) within the system
Documented attack patterns abuse exactly the kind of access create_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AnythingLLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_agent:
{
"version": "1",
"default": "deny",
"tools": {
"create_agent": {
"limits": [
{
"counter": "create_agent_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_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.
Create a new agent. It is categorised as a Write tool in the AnythingLLM MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AnythingLLM MCP Server 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 AnythingLLM MCP Server. 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 AnythingLLM MCP Server MCP server (raqueljezweb/anythingllm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AnythingLLM MCP Server, 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.
38 AnythingLLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.