Content Classifier

@garyedgington

访问 MCP Server

15 days ago

Classify text or JSON input into structured categories using Claude AI — with no setup, no API keys, and no credentials required. Connect directly and start classifying immediately. Five built-in presets: sentiment — positive, neutral, negative topic — technology, finance, health, legal, science, sports, other intent — question, request, complaint, feedback, informational urgency — critical, high, medium, low custom — supply your own 2–20 label taxonomy Two tools: classify_content — full access: all presets, custom taxonomies, multi-label output, up to 32KB input. Billed at $0.005 USDC per call via x402 micropayment on Base mainnet. classify_content_trial — free tier: sentiment and topic presets, single-label output, up to 4KB input. No payment required. Every call returns the top label, a confidence score, a ranked list of all labels, and an optional one-sentence reasoning string. Supports plain text and JSON input. Part of the x402 micropayment task market — a network of AI agents that charge per call using on-chain USDC micropayments.

概览工具评论

概览

x402 Content Classifier

Classify text or structured data into categories using Claude AI. Optional confidence scoring and multi-label output. Part of the x402 micropayment task market.

Live service: https://project-classifier-production.up.railway.app (pending deployment)
Smithery: gary-edgington/x402-content-classifier (pending submission)
Payment: $0.005 USDC per call · x402 v2 · Base mainnet

Supported Classification Modes

Preset	Labels	Use case
`sentiment`	positive, neutral, negative	Tone analysis
`topic`	technology, finance, health, legal, science, sports, other	Content routing
`intent`	question, request, complaint, feedback, informational	Support triage
`urgency`	critical, high, medium, low	Prioritization queues
`custom`	caller-supplied taxonomy	Any domain

Endpoints

`POST /v1/classify` — Paid

Requires x402 payment header. $0.005 USDC on Base mainnet.

Request body:

{
  "input": "<text or JSON string to classify>",
  "input_type": "text",
  "preset": "sentiment",
  "taxonomy": [],
  "multi_label": false,
  "explain": true
}

Query params:

?multi_label=true — return ranked list of all matching labels rather than a single top label.

Response (200):

{
  "label": "positive",
  "confidence": 0.92,
  "labels": [
    {"label": "positive", "confidence": 0.92},
    {"label": "neutral", "confidence": 0.06},
    {"label": "negative", "confidence": 0.02}
  ],
  "reasoning": "The text expresses strong satisfaction and approval with no negative indicators.",
  "meta": {
    "preset": "sentiment",
    "multi_label": false,
    "input_type": "text",
    "model": "claude-haiku-4-5"
  }
}

Response (402 — no payment):

{
  "x402Version": 2,
  "accepts": [{
    "scheme": "exact",
    "network": "eip155:8453",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "5000",
    "payTo": "0x8fC4006534801c17A3368075A1Fb3b3C511EdB1F",
    "maxTimeoutSeconds": 300
  }],
  "error": "Payment required"
}

`POST /v1/classify/trial` — Free

No payment required. Same classification logic. Limits: 4KB max input, single-label only, sentiment and topic presets only.

`GET /health`

{ "status": "ok", "service": "classifier-agent", "version": "0.1.0" }

MCP Tool

This service exposes a single MCP tool via SSE transport for use with MCP-compatible agents and Claude Desktop.

SSE endpoint: https://project-classifier-production.up.railway.app/sse

`classify_content`

Classify text or structured data into a category using Claude AI.

Parameter	Type	Required	Description
`input`	string	✅	Text or JSON string to classify
`input_type`	string	—	`text` (default) or `json`
`preset`	string	—	`sentiment`, `topic`, `intent`, `urgency`, or `custom`
`taxonomy`	array	—	Custom label list (required when `preset=custom`)
`multi_label`	boolean	—	If true, return ranked label list
`explain`	boolean	—	If true, include reasoning string

x402 Payment Details

Setting	Value
Network	Base mainnet (`eip155:8453`)
USDC contract	`0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913`
Amount	`5000` atomic units ($0.005)
Receiving wallet	`0x8fC4006534801c17A3368075A1Fb3b3C511EdB1F`
Facilitator	`https://api.cdp.coinbase.com/platform/v2/x402`
EIP-712 domain	`USD Coin`

Pipeline Example

Agents can chain services via the A2A hub discovery manifest:

Raw CSV → Formatter (/v1/format) → Classifier (/v1/classify)
Raw JSON → Schema Checker (/v1/schema-check) → Classifier (/v1/classify)

Each hop settles independently on Base mainnet via x402.

Ecosystem

This service is part of a three-service x402 task market:

SchemaCheck Agent — JSON Schema validation
Formatter — data format conversion
Classifier (this service) — content classification
A2A Hub — service discovery

Full capability manifest: GET https://project-a2a-production.up.railway.app/v1/capabilities

在 Playground 中尝试

服务器配置

{
  "mcpServers": {
    "x402-classifier": {
      "url": "https://web-production-2d1051.up.railway.app/sse"
    }
  }
}

Build with ShipAny.