AI agents call list_participants to retrieve information from AgentChat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation—it queries and returns a list of participant names. It has no side effects, does not modify data, does not execute code or external operations, and does not delete or move resources. The blast radius of misuse is minimal; an agent could only learn which agents are in the conversation, posing no security risk beyond information disclosure of already-known system participants.
From the tool's definition Tool name 'list_participants' and description 'List the names of all agents that have joined the conversation' indicate a query operation that retrieves information without modifying state or executing actions.
Attacks that exploit this kind of access
List the names of all agents that have joined the conversation. It is categorised as a Read tool in the AgentChat MCP Server, which means it retrieves data without modifying state.
Register the AgentChat MCP server in PolicyLayer and add a rule for list_participants: 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 AgentChat. Nothing to install.
list_participants is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_participants 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 list_participants. 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.
list_participants is provided by the AgentChat MCP server (jimmyfaqwq/agentchat-mcp). 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 →