AI agents call list_projects to retrieve information from MCP Files without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or enumerates existing project identifiers from the filesystem. It performs a read-only query operation that does not create, modify, delete, or execute any code. The action is informational only, suitable for discovery of available projects. The low severity reflects minimal blast radius—an agent listing projects cannot harm data or systems, only gain visibility of what exists.
From the tool's definition Tool name is 'list_projects' and description states it 'List available project IDs', which is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List available project IDs (UUID directories) when projects are enabled for the API key. It is categorised as a Read tool in the MCP Files MCP Server, which means it retrieves data without modifying state.
Register the MCP Files 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 Files. 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 Files MCP server (tspspi/mcpfiles). 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 →