Medium Risk

add_sample_field

Add a new field with an explicit type to a

How to control add_sample_field ↓

What add_sample_field does on FiftyOne MCP Server

AI agents use add_sample_field 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 add_sample_field needs a policy

Adding a field to a dataset is a write operation that creates new metadata/schema elements. It is reversible (fields can be removed) and does not delete data or execute arbitrary code. The medium severity reflects that schema changes could affect downstream processing, but the operation is non-destructive and can be undone. Confidence slightly reduced due to incomplete description.

From the tool's definition Tool name 'add_sample_field' and description 'Add a new field with an explicit type to a' indicate creation/modification of dataset schema. This modifies dataset structure reversibly.

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

How to control add_sample_field

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 add_sample_field:

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

add_sample_field 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 add_sample_field

What does the add_sample_field tool do? +

Add a new field with an explicit type to a. 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 add_sample_field? +

Register the FiftyOne MCP Server MCP server in PolicyLayer and add a rule for add_sample_field: 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 add_sample_field? +

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

Can I rate-limit add_sample_field? +

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

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

add_sample_field 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.