Remove an item from a GitHub Project V2
AI agents call remove_project_item to permanently remove resources in GitHub Projects MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a project item is an irreversible deletion action - once an item is removed from a GitHub Project V2, it cannot be recovered through the same interface. This matches the Destructive category as it permanently removes data. The blast radius is high since misuse could remove critical project tracking items, disrupting team workflows and losing project management data.
From the tool's definition Remove an item from a GitHub Project V2
Attacks that exploit this kind of access
Remove an item from a GitHub Project V2. It is categorised as a Destructive tool in the GitHub Projects MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitHub Projects MCP Server MCP server in PolicyLayer and add a rule for remove_project_item: 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 Projects MCP Server. Nothing to install.
remove_project_item 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_project_item 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_project_item. 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_project_item is provided by the GitHub Projects MCP Server MCP server (lexmata/github-projects-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 →