広告掲載
MCP.so
ログイン

Content Classifier MCP Server

@garyedgington

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

garyedgington

投稿者

Gary Edgington

Content Classifier MCP Server について

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.

#nlp#classification#text-analysis#sentiment#x402#ai-agents#micropayments

Content Classifier MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

Content Classifier MCP Server のツール

2

Classify text or JSON input into a category using Claude AI. Supports five built-in presets and caller-supplied custom taxonomies. Returns the top label, confidence score, ranked list of all labels, and an optional one-sentence reasoning string. Args: input: Text or JSON string to classify. Max 32KB. input_type: "text" (default) or "json". When json, the string is parsed before classification. preset: Built-in taxonomy — sentiment | topic | intent | urgency | custom. sentiment: positive, neutral, negative. topic: technology, finance, health, legal, science, sports, other. intent: question, request, complaint, feedback, informational. urgency: critical, high, medium, low. custom: use your own labels via the taxonomy parameter. taxonomy: Required when preset=custom. List of 2–20 label strings. multi_label: When True, labels array contains all taxonomy labels ranked by confidence. explain: When True, include a one-sentence reasoning string. Returns: label (str), confidence (float), labels (list), reasoning (str|null), meta (dict).

Classify text into a category using Claude AI (free trial — limited presets, 4KB max). Supports sentiment and topic presets only. Multi-label is always disabled. Use classify_content for full access: all presets, custom taxonomies, 32KB input. Args: input: Text to classify. Max 4KB on trial. preset: sentiment (positive/neutral/negative) or topic (technology/finance/health/…). explain: When True, include a one-sentence reasoning string. Returns: label (str), confidence (float), labels (list), reasoning (str|null), meta (dict).

概要

What is Content Classifier?

Content Classifier is an MCP server that classifies text or structured data into categories using Claude AI. It supports preset taxonomies (sentiment, topic, intent, urgency) or custom user-defined labels, with optional confidence scoring and multi‑label output. The server is part of the x402 micropayment task market and charges $0.005 USDC per call on Base mainnet.

How to use Content Classifier?

The server exposes a single MCP tool classify_content via SSE transport at https://project-classifier-production.up.railway.app/sse. REST endpoints are also available: POST /v1/classify (paid, requires x402 payment header) and POST /v1/classify/trial (free, with limits). Provide parameters such as input, preset, taxonomy, multi_label, and explain to classify content.

Key features of Content Classifier

  • Classify text or JSON into five built‑in presets or a custom taxonomy
  • Optional multi‑label output returning a ranked list of all matching labels
  • x402 micropayment integration – $0.005 USDC per call on Base mainnet
  • Free trial endpoint with 4KB input limit and two presets (sentiment, topic)
  • MCP tool over SSE transport for Claude Desktop and MCP‑compatible agents
  • Chains with Formatter and SchemaCheck agents in the x402 task market

Use cases of Content Classifier

  • Analyze sentiment of user feedback or social media posts
  • Route content by topic (technology, finance, health, etc.) for content management
  • Prioritize support tickets by urgency level (critical, high, medium, low)
  • Classify customer intent (question, request, complaint) for triage workflows
  • Build custom classification pipelines for domain‑specific taxonomies

よくある質問

1

How does payment work for Content Classifier?

Each paid classification call costs $0.005 USDC on Base mainnet via the x402 v2 protocol. The payment is settled independently per request.

2

What classification presets are available?

Built‑in presets are `sentiment`, `topic`, `intent`, `urgency`, and `custom`. When using `custom`, you must provide a taxonomy array of your own labels.

3

Is there a free way to try Content Classifier?

Yes. The `POST /v1/classify/trial` endpoint is free but limited to 4KB input size, single‑label output only, and only the `sentiment` and `topic` presets.

4

What data does Content Classifier return?

The response includes a `label`, `confidence` score, optional `reasoning` string, and a ranked `labels` array when `multi_label` is true. Metadata such as the preset and model is also returned.

5

Can I use my own categories instead of the presets?

Yes. Set `preset` to `"custom"` and include a `taxonomy` array of your labels in the request body.

コメント

「その他」の他のコンテンツ

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

広告掲載