Search for GitHub repositories
AI agents call search-repos to retrieve information from GitHub 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 public repository metadata based on search criteria. It is a read-only query operation with no capability to modify state, execute code, or trigger external actions. The blast radius of misuse is minimal—an agent could only enumerate repositories, not change them or access private data beyond normal GitHub API permissions.
From the tool's definition Tool name 'search-repos' and description 'Search for GitHub repositories' indicate a query operation with no side effects. Searching is a retrieval operation that does not modify, execute, or delete data.
Attacks that exploit this kind of access
Search for GitHub repositories. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for 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 MCP Server. Nothing to install.
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 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 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.
search-repos is provided by the GitHub MCP Server MCP server (ualusham/mcp-github). 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 →