AI agents call read_repository_code 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.
This tool retrieves code without modification or side effects. The 'read_' prefix strongly indicates a query operation. Even though the description is empty, context from the server description and sibling tools confirms this is a data retrieval function. No evidence suggests code execution, deletion, or modifications.
From the tool's definition Tool name 'read_repository_code' indicates retrieval of code from repositories. Server description explicitly mentions 'reading repository code' as a capability.
Attacks that exploit this kind of access
read_repository_code. 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 read_repository_code: 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.
read_repository_code 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 read_repository_code 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 read_repository_code. 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.
read_repository_code 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 →