AI agents call search_repositories to retrieve information from Gitlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations on repositories are queries that retrieve metadata or code listings without modifying data. Given the server's focus on reading and analyzing GitLab repositories, and the absence of any language suggesting mutations, destructive actions, or execution, this is classified as a Read operation with low severity.
From the tool's definition Tool name is 'search_repositories' and server description indicates it provides tools for 'listing projects' and 'reading repository code'. The sibling tools are predominantly Read operations (list_*, read_*, get_*).
Attacks that exploit this kind of access
search_repositories. It is categorised as a Read tool in the Gitlab MCP Server, which means it retrieves data without modifying state.
Register the Gitlab MCP server in PolicyLayer and add a rule for search_repositories: 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. Nothing to install.
search_repositories 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_repositories 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_repositories. 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_repositories is provided by the Gitlab MCP server (kopiloto/mcp-gitlab-server). 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 →