list_mr_discussions_tool
AI agents call list_mr_discussions_tool to retrieve information from MCP Gitlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves or queries merge request discussion data with no apparent side effects. While the description is empty, the name pattern 'list_*' strongly suggests a read operation. This is low severity because listing discussions does not modify data, execute code, or affect system state beyond information disclosure.
From the tool's definition Tool name 'list_mr_discussions_tool' indicates a retrieval operation on merge request discussions. The 'list' prefix is characteristic of read-only query operations that enumerate or fetch existing data without modification.
Attacks that exploit this kind of access
list_mr_discussions_tool. It is categorised as a Read tool in the MCP Gitlab MCP Server, which means it retrieves data without modifying state.
Register the MCP Gitlab MCP server in PolicyLayer and add a rule for list_mr_discussions_tool: 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 MCP Gitlab. Nothing to install.
list_mr_discussions_tool 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 list_mr_discussions_tool 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 list_mr_discussions_tool. 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.
list_mr_discussions_tool is provided by the MCP Gitlab MCP server (mcp-gitlab-crunchtools). 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 →