Send a message to the selected agent and get a response
AI agents invoke chat_with_agent to trigger actions in Society ElizaOS Connector MCP. 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.
Chatting with an AI agent is an Execute-class action because the agent may perform arbitrary downstream operations (web searches, file edits, API calls, shell commands) depending on the message sent. The blast radius is high since the agent's actions are unbounded and determined by the input arguments.
From the tool's definition "Send a message to the selected agent and get a response" — triggers an ElizaOS agent to process input and produce effects that depend on the agent's capabilities and the message content
Documented attack patterns abuse exactly the kind of access chat_with_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Society ElizaOS Connector MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for chat_with_agent:
{
"version": "1",
"default": "deny",
"tools": {
"chat_with_agent": {
"limits": [
{
"counter": "chat_with_agent_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}chat_with_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.
Send a message to the selected agent and get a response. It is categorised as a Execute tool in the Society ElizaOS Connector MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Society ElizaOS Connector MCP server in PolicyLayer and add a rule for chat_with_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 Society ElizaOS Connector MCP. Nothing to install.
chat_with_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 chat_with_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 chat_with_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.
chat_with_agent is provided by the Society ElizaOS Connector MCP server (wearesociety/elizaos_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Society ElizaOS Connector MCP, 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.
4 Society ElizaOS Connector MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.