AI agents call list_agents_by_project to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a list of active agents for a given project. It performs no mutations, deletions, executions, or financial operations. It is a straightforward read operation with minimal security impact if misused by an AI agent—it merely exposes visibility into which agents are active.
From the tool's definition Tool name 'list_agents_by_project' and description 'List agents currently active on a project' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List agents currently active on a project. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for list_agents_by_project: 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 Mementos. Nothing to install.
list_agents_by_project 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_agents_by_project 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_agents_by_project. 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_agents_by_project is provided by the Mementos MCP server (@hasna/mementos). 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 →