Content Classifier

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

FAQ from Content Classifier

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.

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.

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.

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.

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.