memvid_put · Memvid MCP: Risk & Policy

WHAT IT DOES

What memvid_put does on Memvid

AI agents use memvid_put 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.

WHY IT NEEDS A POLICY

Why memvid_put needs a policy

This tool creates or modifies data in a persistent memory system without deleting or overwriting existing content irreversibly. The 'Add' operation is characteristic of Write category tools.

From the tool's definition Tool description states 'Add content to a memory file from a file or directory'. The verb 'Add' combined with the capability to ingest files, directories, and optional vector embeddings indicates reversible modification of a memory file (.mv2).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memvid_put Rate-limited

memvid_put stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "memvid_put": {
      "limits": [
        {
          "counter": "memvid_put_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Memvid, so you can run agents against it safely.

FAQ

Questions about memvid_put

What does the memvid_put tool do? +

Add content to a memory file from a file or directory. Supports: text, markdown, code, PDF, images (OCR). Use embed=true for vector embeddings (semantic search). Args: file: Absolute path to .mv2 file input: Absolute path to file/directory to ingest recursive: Include subdirectories when input is a directory parallel: Process files in parallel for faster ingestion embed: Generate vector embeddings (requires embedder.toml configuration) log: Path to log file for detailed operation logging Returns: {. 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.

How do I enforce a policy on memvid_put? +

Register the Memvid MCP server in PolicyLayer and add a rule for memvid_put: 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.

What risk level is memvid_put? +

memvid_put is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit memvid_put? +

Yes. Add a rate_limit block to the memvid_put 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.

How do I block memvid_put completely? +

Set action: deny in the PolicyLayer policy for memvid_put. 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.

What MCP server provides memvid_put? +

memvid_put 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.