AI agents call task_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.
This is a query/list operation that retrieves data without side effects. The tool only reads task metadata (id, ticket_id, status) from a local SQLite database and returns results. It has no capability to modify, delete, or execute operations. The blast radius of misuse is minimal—an agent cannot cause harm by listing tasks.
From the tool's definition Tool returns task IDs with status only; explicitly directs users to task_get for details. No modification, deletion, or execution capability.
Attacks that exploit this kind of access
PROJECT MANAGEMENT (TPM): List task IDs with status. Returns id, ticket_id, status only - use task_get for details. 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 task_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.
task_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 task_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 task_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.
task_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 →