AI agents invoke invoke_agent to trigger actions in AnythingLLM MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
invoke_agent runs code/logic (the agent) triggered by arguments, making it an Execute category tool. Severity is high because an agent invocation can perform various operations (queries, modifications, deletions, API calls) depending on the agent's design and input, creating significant blast radius if misused by an AI without proper safeguards.
From the tool's definition Tool description states 'Invoke an agent with input' — this triggers execution of an agent with user-supplied arguments.
Documented attack patterns abuse exactly the kind of access invoke_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 invoke_agent:
{
"version": "1",
"default": "deny",
"tools": {
"invoke_agent": {
"limits": [
{
"counter": "invoke_agent_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}invoke_agent stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Invoke an agent with input. It is categorised as a Execute tool in the AnythingLLM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AnythingLLM MCP Server MCP server in PolicyLayer and add a rule for invoke_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.
invoke_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the invoke_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 invoke_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.
invoke_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.