AI agents call project_list to retrieve information from Tpm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays existing project data from the SQLite database without creating, modifying, or deleting any records. It has no capability to execute code, trigger external operations, or commit financial transactions. The blast radius of misuse is minimal—an attacker could view project information but cannot alter it or cause irreversible harm.
From the tool's definition Tool name 'project_list' and description 'List projects in an organization' indicate a retrieval operation with no modification or side effects. This is a data query operation.
Attacks that exploit this kind of access
PROJECT MANAGEMENT: List projects in an organization. It is categorised as a Read tool in the Tpm MCP Server, which means it retrieves data without modifying state.
Register the Tpm MCP server in PolicyLayer and add a rule for project_list: 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 Tpm. Nothing to install.
project_list 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 project_list 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 project_list. 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.
project_list is provided by the Tpm MCP server (urjitbhatia/tpm-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 →