Set the name for the MCP server project
AI agents use set_project_name to create or update resources in MCP Project Initializer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Project Initializer environment.
An AI agent can call set_project_name faster than any human can review — one bad instruction and it creates or modifies resources in MCP Project Initializer by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Set the name for the MCP server project. It is categorised as a Write tool in the MCP Project Initializer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Project Initializer MCP server in PolicyLayer and add a rule for set_project_name: 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 MCP Project Initializer. Nothing to install.
set_project_name 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 set_project_name 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 set_project_name. 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.
set_project_name is provided by the MCP Project Initializer MCP server (syndicats/mcp-initializer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.