AI agents call repository_list to retrieve information from Semaphore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple query/retrieval operation to enumerate repositories within a project. It has no ability to create, modify, delete, execute code, or affect external systems. The blast radius of misuse is minimal—an AI agent listing repositories cannot cause harm beyond information disclosure of repository metadata already scoped to an authenticated project context.
From the tool's definition Tool name is 'repository_list' and description states 'List all repositories in a project.' The verb 'List' is a read-only operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
List all repositories in a project. It is categorised as a Read tool in the Semaphore MCP Server, which means it retrieves data without modifying state.
Register the Semaphore MCP server in PolicyLayer and add a rule for repository_list: 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 Semaphore. Nothing to install.
repository_list 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 repository_list 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 repository_list. 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.
repository_list is provided by the Semaphore MCP server (vitexsoftware/semaphore-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 →