get-comments-by-user
AI agents call get-comments-by-user to retrieve information from Trello MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests querying/fetching comments associated with a user in Trello, which is a read operation with no side effects. No data is created, modified, deleted, or executed. The empty description prevents confirmation of exact behavior, but the naming pattern is unambiguous for a retrieval operation. Severity is low because reading comments poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'get-comments-by-user' indicates data retrieval with no modifying action. The 'get-' prefix is a standard convention for read-only operations. Tool description is empty, which lowers confidence slightly.
Attacks that exploit this kind of access
get-comments-by-user. It is categorised as a Read tool in the Trello MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trello MCP Server MCP server in PolicyLayer and add a rule for get-comments-by-user: 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 Trello MCP Server. Nothing to install.
get-comments-by-user 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-comments-by-user 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-comments-by-user. 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-comments-by-user is provided by the Trello MCP Server MCP server (praveencs87/trello-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 →