Medium Risk

tag_samples

Add tags to samples in a dataset. Optionally

How to control tag_samples ↓

What tag_samples does on FiftyOne MCP Server

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

Medium Risk

Why tag_samples needs a policy

This tool creates or modifies metadata (tags) on existing samples. It is a Write-category operation because it changes dataset state in a reversible manner—tags can be removed or updated. The severity is medium because misuse could corrupt or pollute dataset annotations, affecting downstream ML workflows, but the impact is limited to metadata and reversible.

From the tool's definition Tool name 'tag_samples' and description 'Add tags to samples in a dataset' indicate a modification operation.

Documented attack patterns abuse exactly the kind of access tag_samples gives an agent:

How to control tag_samples

PolicyLayer is an MCP gateway — it sits between your AI agents and FiftyOne MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for tag_samples:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "tag_samples": {
      "limits": [
        {
          "counter": "tag_samples_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

tag_samples 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.

  1. Create a free account and register FiftyOne MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about tag_samples

What does the tag_samples tool do? +

Add tags to samples in a dataset. Optionally. It is categorised as a Write tool in the FiftyOne MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on tag_samples? +

Register the FiftyOne MCP Server MCP server in PolicyLayer and add a rule for tag_samples: 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 FiftyOne MCP Server. Nothing to install.

What risk level is tag_samples? +

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

Can I rate-limit tag_samples? +

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

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

tag_samples is provided by the FiftyOne MCP Server MCP server (voxel51/fiftyone-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every FiftyOne MCP Server tool call.

Start from FiftyOne MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

47 FiftyOne MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.