github_trending
AI agents call github_trending to retrieve information from Mcp Everything without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves trending repositories or projects from GitHub, which is a read-only query operation with no side effects. It does not modify, execute, delete, or create any data, nor does it involve financial operations. The empty description limits detail, but the name and sibling tools (all data retrieval focused) strongly indicate it is a data-fetching utility with low blast radius if misused.
From the tool's definition Tool name 'github_trending' and context indicating it is part of a bundle for accessing GitHub data directly from conversations, alongside other data retrieval tools like arxiv_get_paper, books_search, and country_info.
Attacks that exploit this kind of access
github_trending. It is categorised as a Read tool in the Mcp Everything MCP Server, which means it retrieves data without modifying state.
Register the Mcp Everything MCP server in PolicyLayer and add a rule for github_trending: 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 Everything. Nothing to install.
github_trending 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_trending 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_trending. 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_trending is provided by the Mcp Everything MCP server (wellix260/mcp-everything). 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 →