Set up KeepGoing hooks and instructions. Use scope
AI agents use setup_project to create or update resources in KeepGoing MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KeepGoing MCP Server environment.
This tool performs setup operations that create or modify project configuration (hooks and instructions), making it a Write operation. It is not Read (which would only retrieve information), not Execute (which would run arbitrary code with variable effects), and not Destructive (the setup can be undone by removing hooks).
From the tool's definition The tool description states 'Set up KeepGoing hooks and instructions' which indicates it creates or modifies configuration and system hooks within a project. This is a reversible change operation that establishes persistent tracking mechanisms.
Attacks that exploit this kind of access
Set up KeepGoing hooks and instructions. Use scope. It is categorised as a Write tool in the KeepGoing MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KeepGoing MCP Server MCP server in PolicyLayer and add a rule for setup_project: 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 KeepGoing MCP Server. Nothing to install.
setup_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the setup_project 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 setup_project. 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.
setup_project is provided by the KeepGoing MCP Server MCP server (keepgoing-dev/mcp-server). 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 →