list_user_orgs
AI agents call list_user_orgs to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list' verb combined with 'user_orgs' strongly suggests this tool queries and returns organization data without modifying state. Despite the empty description lowering confidence slightly, the semantic structure of the name places this firmly in the Read category with minimal risk—listing organizations is a non-destructive, informational operation that cannot cause data loss, execute code, or trigger side…
From the tool's definition Tool name 'list_user_orgs' indicates a retrieval operation (list) that queries organizations associated with a user; no description provided but naming convention clearly indicates read-only data retrieval.
Attacks that exploit this kind of access
list_user_orgs. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for list_user_orgs: 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 MCP Server. Nothing to install.
list_user_orgs 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 list_user_orgs 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 list_user_orgs. 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.
list_user_orgs is provided by the GitHub MCP Server MCP server (software-engineer-mj/github-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 →