Search for repositories
AI agents call gh_search_repos to retrieve information from GitHub CLI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves repository metadata without modifying, deleting, or executing any operations. It is purely informational and read-only. The low severity reflects minimal blast radius—an AI agent misusing search would at worst retrieve unintended repository information, not cause operational damage.
From the tool's definition Tool name 'gh_search_repos' and description 'Search for repositories' indicate a query operation with no side effects. Search is a retrieval operation.
Attacks that exploit this kind of access
Search for repositories. It is categorised as a Read tool in the GitHub CLI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub CLI MCP Server MCP server in PolicyLayer and add a rule for gh_search_repos: 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 CLI MCP Server. Nothing to install.
gh_search_repos 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 gh_search_repos 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 gh_search_repos. 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.
gh_search_repos is provided by the GitHub CLI MCP Server MCP server (munch-group/gh-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 →