Create a new .mv2 memory file for storing AI agent memories. The .mv2 format is a SQLite-based memory store supporting: - Full-text lexical search (Tantivy) - Vector similarity search (embeddings) - Temporal indexing Args: file: Absolute path where the .mv2 file will be created Returns: JSON with...
AI agents use memvid_create 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 a new file, which is a reversible Write operation. The blast radius is medium because: (1) it creates a new data store that could be used to persist harmful information or state, (2) an agent could create files in unexpected locations if path validation is bypassed, and (3) excessive file creation could exhaust storage.
From the tool's definition Tool description states "Create a new .mv2 memory file" and takes a file path argument, creating a new persistent data storage artifact.
Attacks that exploit this kind of access
Create a new .mv2 memory file for storing AI agent memories. The .mv2 format is a SQLite-based memory store supporting: - Full-text lexical search (Tantivy) - Vector similarity search (embeddings) - Temporal indexing Args: file: Absolute path where the .mv2 file will be created Returns: JSON with creation status and file path Errors: - File already exists at that path - Invalid path or permission denied - Path outside allowed roots. 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 memvid_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 Memvid. Nothing to install.
memvid_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 memvid_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 memvid_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.
memvid_create is provided by the Memvid MCP server (tapiocapioca/memvid-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 →