embedding_write · Zvec MCP: Risk & Policy

WHAT IT DOES

What embedding_write does on Zvec

AI agents use embedding_write to create or update resources in Zvec — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zvec environment.

WHY IT NEEDS A POLICY

Why embedding_write needs a policy

An AI agent can call embedding_write faster than any human can review — one bad instruction and it creates or modifies resources in Zvec by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

embedding_write Rate-limited

embedding_write 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": {
    "embedding_write": {
      "limits": [
        {
          "counter": "embedding_write_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 Zvec, so you can run agents against it safely.

FAQ

Questions about embedding_write

What does the embedding_write tool do? +

embedding_write. It is categorised as a Write tool in the Zvec MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on embedding_write? +

Register the Zvec MCP server in PolicyLayer and add a rule for embedding_write: 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 Zvec. Nothing to install.

What risk level is embedding_write? +

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

Can I rate-limit embedding_write? +

Yes. Add a rate_limit block to the embedding_write 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 embedding_write completely? +

Set action: deny in the PolicyLayer policy for embedding_write. 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 embedding_write? +

embedding_write is provided by the Zvec MCP server (zvec-ai/zvec-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.