Search for trending AI/ML GitHub repositories
AI agents call search_github_repos to retrieve information from AI Research MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves publicly available GitHub repository data. It performs a read-only search operation that aggregates trending repositories without creating, modifying, deleting, or executing any code. There is no data mutation, destructive action, code execution, or financial transaction involved. The minimal risk stems only from potential information disclosure of what the user is researching.
From the tool's definition Tool name is 'search_github_repos' and description states 'Search for trending AI/ML GitHub repositories'.
Attacks that exploit this kind of access
Search for trending AI/ML GitHub repositories. It is categorised as a Read tool in the AI Research MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AI Research MCP Server MCP server in PolicyLayer and add a rule for search_github_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 AI Research MCP Server. Nothing to install.
search_github_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_github_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_github_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_github_repos is provided by the AI Research MCP Server MCP server (nanyang12138/ai-research-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 →