Search issues by full-text query within a project or group. Maps to GET /:scope/:id/search?scope=issues.
AI agents call search_issues 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.
This tool retrieves or queries issue data via a GET endpoint without creating, modifying, deleting, or executing any operations. It is a standard search/list operation with no blast radius if misused by an AI agent—the worst outcome would be accessing visible issues the user already has permissions to view.
From the tool's definition Tool description states 'Search issues by full-text query' and 'Maps to GET /:scope/:id/search?scope=issues', indicating a read-only query operation with no data modification or side effects.
Attacks that exploit this kind of access
Search issues by full-text query within a project or group. Maps to GET /:scope/:id/search?scope=issues. 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 search_issues: 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.
search_issues 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 search_issues 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 search_issues. 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.
search_issues is provided by the Mcp Gitlab MCP server (wanadev/gitlab-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 →