hf_inference.nlp.zero_shot

SERVERApibase SOURCEapibase-mcp-client

Medium RISK CLASS

Category Write

Parameters 42 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-whiteknightonhorse-apibase/hf-inference.nlp.zero-shot.md

WHAT IT DOES

What hf_inference.nlp.zero_shot does on Apibase

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

Parameter	Type	Required	Description
`text`	string	Yes	Input text to process. Maximum ~10,000 characters depending on model context window.
`model`	string	—	HuggingFace model ID to use for zero-shot classification. Default: "facebook/bart-large-mnli" (MNLI-trained, accurate but slower). Alternatives: "cross-encoder/
`multi_label`	boolean	—	If true, scores are independent for each label (text can match multiple categories simultaneously). If false (default), scores are mutually exclusive and sum to
`candidate_labels`	array	Yes	List of candidate category labels to classify the text into (2–20 labels). Example: ["politics", "sports", "technology", "entertainment"]. Labels can be any des

Parameters from the server's own tool schema.

RISK

Why hf_inference.nlp.zero_shot is rated Medium

An AI agent can call hf_inference.nlp.zero_shot faster than any human can review: one bad instruction and it creates or modifies resources in Apibase by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs hf_inference.nlp.zero_shot safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Apibase, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For hf_inference.nlp.zero_shot, this is the rule to start with:

hf_inference.nlp.zero_shot Rate-limited

hf_inference.nlp.zero_shot 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": {
    "hf_inference.nlp.zero_shot": {
      "limits": [
        {
          "counter": "hf_inference.nlp.zero_shot_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Apibase, apply this rule, and every hf_inference.nlp.zero_shot call is checked against it from then on.

FAQ

Questions about hf_inference.nlp.zero_shot

What does the hf_inference.nlp.zero_shot tool do? +

Classify text into any custom set of categories without requiring model fine-tuning or training data. Provide a list of 2–20 candidate labels; the model determines which best describes the input text. Returns labels ranked by confidence score. Supports multi-label mode (text can match multiple categories). Default model: facebook/bart-large-mnli. Ideal for routing, content moderation, intent detection, and ad-hoc categorization tasks. It is categorised as a Write tool in the Apibase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does hf_inference.nlp.zero_shot accept? +

hf_inference.nlp.zero_shot accepts 4 parameters: text, model, multi_label, candidate_labels. Required: text, candidate_labels. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on hf_inference.nlp.zero_shot? +

Register the Apibase MCP server in PolicyLayer and add a rule for hf_inference.nlp.zero_shot: 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 Apibase. Nothing to install.

What risk level is hf_inference.nlp.zero_shot? +

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

Can I rate-limit hf_inference.nlp.zero_shot? +

Yes. Add a rate_limit block to the hf_inference.nlp.zero_shot 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 hf_inference.nlp.zero_shot completely? +

Set action: deny in the PolicyLayer policy for hf_inference.nlp.zero_shot. 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 hf_inference.nlp.zero_shot? +

hf_inference.nlp.zero_shot is provided by the Apibase MCP server (apibase-mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Apibase, and thousands of servers like it.

This server

All 1384 Apibase tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →