AI agents use create_or_get_project to create or update resources in Handoff — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Handoff environment.
This tool creates or modifies project data in a shared memory hub. While retrieval is a read operation, the 'create' capability makes this a Write action. The severity is medium because misuse could result in unauthorized project creation or modification in a shared system, affecting other agents' workflows, but the impact is reversible and limited to project metadata rather than core system integrity or data…
From the tool's definition Tool description states 'Initialize or retrieve a project' — initialization implies creating new project records, which is a reversible write operation. The verb 'create_or_get' explicitly indicates data creation capability.
Attacks that exploit this kind of access
Initialize or retrieve a project in the context hub. It is categorised as a Write tool in the Handoff MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Handoff MCP server in PolicyLayer and add a rule for create_or_get_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 Handoff. Nothing to install.
create_or_get_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 create_or_get_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 create_or_get_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.
create_or_get_project is provided by the Handoff MCP server (juan-severiano/handoff-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 →