AI agents call github.search-repos to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries publicly available GitHub repository information based on search criteria. It does not create, modify, delete, or execute any operations—it simply searches and returns results. The full query syntax mentioned allows flexible filtering but remains a read-only operation. The blast radius of misuse is minimal; an attacker could enumerate repositories but cannot modify or delete them.
From the tool's definition Tool name 'github.search-repos' and description 'Search GitHub repositories' indicate a query/search operation with no modification of data or side effects.
Attacks that exploit this kind of access
Search GitHub repositories with the full query syntax (e.g. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for github.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 Mcp. Nothing to install.
github.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 github.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 github.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.
github.search-repos is provided by the MCP server (@2sio/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 →