list_repositories
AI agents call list_repositories to retrieve information from GitHub Summary MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves repository metadata without modifying data. It serves a foundational read operation to support the summary generation workflow. No side effects, code execution, or data modification implied. Low severity as it merely enumerates resources the user already has access to.
From the tool's definition Tool name 'list_repositories' indicates a retrieval operation. Server description mentions 'analyzing commits across all repositories a user owns or contributes to,' implying the tool queries repository metadata.
Attacks that exploit this kind of access
list_repositories. It is categorised as a Read tool in the GitHub Summary MCP MCP Server, which means it retrieves data without modifying state.
Register the GitHub Summary MCP server in PolicyLayer and add a rule for list_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 GitHub Summary MCP. Nothing to install.
list_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 list_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 list_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.
list_repositories is provided by the GitHub Summary MCP server (muhammadzaeemaltaf/github-summary-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 →