List all project names that have memories.
AI agents call list_projects to retrieve information from mcp-Agentmemory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates existing project names from the memory system. It performs a simple query with no capacity to modify, execute code, delete data, or affect other systems. The blast radius of misuse is minimal — an attacker could discover what projects exist but cannot alter them or access their contents without additional tool invocation. Classified as Read with low severity.
From the tool's definition Tool name is 'list_projects' and description states it 'List[s] all project names' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all project names that have memories. It is categorised as a Read tool in the mcp-Agentmemory MCP Server, which means it retrieves data without modifying state.
Register the mcp-Agentmemory MCP server in PolicyLayer and add a rule for list_projects: 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 mcp-Agentmemory. Nothing to install.
list_projects 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_projects 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_projects. 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_projects is provided by the mcp-Agentmemory MCP server (obidel/agentmemory). 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 →