Skip to main content
Glama

Feegate AI Agent data marketplace catalog & platform metrics

hugging-face-2.hugging_face_export

Read-onlyIdempotent

Ask "read Hugging Face 开源模型生态索引 beyond the free sample" — $0.09 for a per-snapshot AES-256-GCM decryption license. Full original data is kept on an authenticated private origin; the public endpoint serves ciphertext only. Present a valid FeeGate payment credential to the origin detail gateway to receive plaintext. | 付费购买当前快照的解密授权;完整记录仅在认证私有源站,公开面只有密文。需向源站 detail 网关出示平台付款凭证才能取得明文;未付款无法读取全部记录。

[zh] 供应方资产「Hugging Face 开源模型生态索引」按次计费 $0.09 USDC(或等值积分)。 入参:无。 [en] Vendor asset "Hugging Face 开源模型生态索引". Paid per call: $0.09 USDC (or prepaid credits). Args: none. 付款/支付头在 MCP 请求头里带(X-Payment / X-Payment-Tx / Authorization: Bearer fg_…),不要放进参数。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "hugging-face-2.hugging_face_export"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses real behavioral context: it costs $0.09 per call, the public endpoint returns only AES-256-GCM ciphertext, and plaintext requires a payment credential presented to an authenticated private origin. It even names the exact transport mechanism (X-Payment / X-Payment-Tx / Authorization: Bearer fg_…) and warns not to put payment in parameters, which is genuinely useful. It stops short of describing failure modes or what an error response looks like when payment is absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The same information is presented three times: an English paywall paragraph, a Chinese translation of it, then a bilingual [zh]/[en] block restating the vendor, price, and arg-free nature. The payment-header instruction is useful but buried at the end. Substantial pruning would make it far easier to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should carry more of the return-shape burden; it does say plaintext versus ciphertext and that full original records live on the private origin, which is the key distinction. However, it does not describe what a successful export payload looks like or its size/format, so an agent knows the payment mechanics but not what it will receive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4, and the description explicitly confirms "入参:无" / "Args: none". The only parameter-adjacent content is the instruction to keep payment headers out of the arguments, which correctly redirects the agent to the MCP transport layer rather than the input schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description frames this as "read Hugging Face 开源模型生态索引 beyond the free sample" and says full original data exists, so the resource is identifiable. But "Ask …" is an unusual framing for a verb, and it never states what an export actually returns (a snapshot of the index? raw records?) in contrast to the sibling digest/status tools. That leaves the operation only loosely distinguished from the free-sample path.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not guidance relative to alternatives such as hugging_face_digest, hugging_face_status, or a preview endpoint, even though those siblings in the catalog suggest a natural sample-first workflow. The only usage instruction is procedural (pay $0.09, present credentials). An agent must infer on its own that this tool is for full-data access after a free sample.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.