AI agents call get_task_comments to retrieve information from Vaiz MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves comments associated with a task—a pure read operation that queries existing data. There is no creation, modification, deletion, or execution of external operations. The blast radius of misuse is minimal: an unauthorized user might view task comments they shouldn't access, but no data is altered or destroyed.
From the tool's definition Tool name 'get_task_comments' with description 'Get all comments for a specific task' indicates retrieval of existing data without modification or side effects.
Attacks that exploit this kind of access
Get all comments for a specific task by database ID or HRID (e.g.,. It is categorised as a Read tool in the Vaiz MCP MCP Server, which means it retrieves data without modifying state.
Register the Vaiz MCP server in PolicyLayer and add a rule for get_task_comments: 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 Vaiz MCP. Nothing to install.
get_task_comments 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 get_task_comments 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 get_task_comments. 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.
get_task_comments is provided by the Vaiz MCP server (vaizcom/vaiz-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 →