AI agents call getTaskComments to retrieve information from Teamwork MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing comments associated with a task. It queries data without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal — an attacker could only view task comments that may already be accessible to the authenticated user, with no ability to alter state or cause irreversible changes.
From the tool's definition Tool name is 'getTaskComments' and description states 'Get comments for a specific task from Teamwork' — both indicate a read-only retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access getTaskComments gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Teamwork MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for getTaskComments:
{
"version": "1",
"default": "deny",
"tools": {
"getTaskComments": {}
}
}getTaskComments is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get comments for a specific task from Teamwork. It is categorised as a Read tool in the Teamwork MCP MCP Server, which means it retrieves data without modifying state.
Register the Teamwork MCP server in PolicyLayer and add a rule for getTaskComments: 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 Teamwork MCP. Nothing to install.
getTaskComments 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 getTaskComments 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 getTaskComments. 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.
getTaskComments is provided by the Teamwork MCP server (vizioz/teamwork-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Teamwork MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
36 Teamwork MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.