Get details of an issue within a certain project
AI agents call get_issue_details to retrieve information from GitLab MR MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries issue data without creating, modifying, deleting, or executing any operations. It is purely informational, consistent with Read category tools like 'get' and 'fetch'. The blast radius of misuse is minimal—an agent could only learn about issue details it queries for, not modify or delete anything. Severity is low due to the passive nature of data retrieval.
From the tool's definition Tool name 'get_issue_details' and description 'Get details of an issue within a certain project' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get details of an issue within a certain project. It is categorised as a Read tool in the GitLab MR MCP MCP Server, which means it retrieves data without modifying state.
Register the GitLab MR MCP server in PolicyLayer and add a rule for get_issue_details: 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 GitLab MR MCP. Nothing to install.
get_issue_details 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_issue_details 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_issue_details. 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_issue_details is provided by the GitLab MR MCP server (kevinlin/gitlab-mr-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 →