Search GitHub repositories.
AI agents call github_search_repos 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 queries GitHub's public repository data and returns results. Search operations are read-only with no side effects, making them low severity. The tool fits the 'Read' category as it retrieves information without any capability to modify, delete, or execute arbitrary actions.
From the tool's definition Tool name 'github_search_repos' indicates a search operation. Description 'Search GitHub repositories' confirms it retrieves/queries data without modifying anything. No verbs suggesting mutation (create, update, delete) or code execution are present.
Attacks that exploit this kind of access
Search GitHub repositories. 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_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 Everything. 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 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 →