remove_collaborator
AI agents call remove_collaborator to permanently remove resources in GitHub MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a collaborator revokes their repository access, which is a destructive and potentially irreversible action (the collaborator loses all permissions immediately). While a collaborator could theoretically be re-added, the act of removal is not automatically undone and can have significant security and access implications.
From the tool's definition Tool name 'remove_collaborator' — the 'remove' prefix strongly implies irreversible deletion of a collaborator's access to a repository.
Attacks that exploit this kind of access
remove_collaborator. It is categorised as a Destructive tool in the GitHub MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for remove_collaborator: 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.
remove_collaborator is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_collaborator 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 remove_collaborator. 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.
remove_collaborator 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 →