AI agents use create_or_open_memory to create or update resources in Memvid — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memvid environment.
This tool creates new memory files or modifies existing ones (reversible operations). It does not delete data (unlike memvid_delete_project), execute arbitrary code, or move money. The ability to initialize/open files represents a Write operation with medium severity due to potential for creating unwanted project context that could mislead downstream operations.
From the tool's definition Tool name 'create_or_open_memory' and description 'Initialize or open a Memvid memory file for a specific project' indicate file creation or modification. Context from sibling tool 'memvid_delete_project' suggests persistent data storage.
Attacks that exploit this kind of access
Initialize or open a Memvid memory file for a specific project. It is categorised as a Write tool in the Memvid MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memvid MCP server in PolicyLayer and add a rule for create_or_open_memory: 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 Memvid. Nothing to install.
create_or_open_memory 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_open_memory 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_open_memory. 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_open_memory is provided by the Memvid MCP server (memvid-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 →