Search for users on GitHub
AI agents call search-users to retrieve information from GitHub Enterprise MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search query against GitHub's user directory. It retrieves data about users without side effects, matching the Read category definition (retrieves or queries data; no side effects). The severity is low because misuse would at most expose publicly available user information, with minimal blast radius for an enterprise environment.
From the tool's definition Tool name 'search-users' and description 'Search for users on GitHub' indicate a query operation that retrieves public user information without modifying, executing code, or causing destructive actions.
Attacks that exploit this kind of access
Search for users on GitHub. It is categorised as a Read tool in the GitHub Enterprise MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub Enterprise MCP Server MCP server in PolicyLayer and add a rule for search-users: 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 Enterprise MCP Server. Nothing to install.
search-users 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-users 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-users. 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-users is provided by the GitHub Enterprise MCP Server MCP server (lessinthought/github-enterprice-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 →