AI agents use project_create to create or update resources in Recap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Recap environment.
This tool creates new persistent data (a project record/directory) in the local markdown-based workspace. It is reversible (projects can be deleted via task_delete or similar), so it falls into Write rather than Destructive.
From the tool's definition Tool description states 'Create a new project' — a write operation that creates new data structures in the user's workspace. The ability to 'seed it from a template' adds configuration flexibility but does not change the fundamental write nature.
Attacks that exploit this kind of access
Create a new project. Optionally seed it from a template:. It is categorised as a Write tool in the Recap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Recap MCP server in PolicyLayer and add a rule for project_create: 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 Recap. Nothing to install.
project_create 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 project_create 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 project_create. 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.
project_create is provided by the Recap MCP server (shivam-singh-git/recap-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 →