Get repository files and directories.
AI agents call get_repository_files to retrieve information from GitLab MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file and directory information from a repository without creating, modifying, or deleting any data. It is purely informational and has no destructive or operational side effects. The low severity reflects the minimal risk of misuse—returning file metadata or contents cannot harm the repository or cause unintended consequences.
From the tool's definition Tool name is 'get_repository_files' and description states 'Get repository files and directories.' The verb 'Get' clearly indicates a read operation with no modification or side effects.
Attacks that exploit this kind of access
Get repository files and directories. It is categorised as a Read tool in the GitLab MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitLab MCP Server MCP server in PolicyLayer and add a rule for get_repository_files: 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 MCP Server. Nothing to install.
get_repository_files 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_repository_files 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_repository_files. 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_repository_files is provided by the GitLab MCP Server MCP server (skmprb/gitlab-clone-mcp-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 →