Content Classifier

Created By
garyedgington19 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.
Overview

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

PresetLabelsUse case
sentimentpositive, neutral, negativeTone analysis
topictechnology, finance, health, legal, science, sports, otherContent routing
intentquestion, request, complaint, feedback, informationalSupport triage
urgencycritical, high, medium, lowPrioritization queues
customcaller-supplied taxonomyAny 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.

ParameterTypeRequiredDescription
inputstringText or JSON string to classify
input_typestringtext (default) or json
presetstringsentiment, topic, intent, urgency, or custom
taxonomyarrayCustom label list (required when preset=custom)
multi_labelbooleanIf true, return ranked label list
explainbooleanIf true, include reasoning string

x402 Payment Details

SettingValue
NetworkBase mainnet (eip155:8453)
USDC contract0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
Amount5000 atomic units ($0.005)
Receiving wallet0x8fC4006534801c17A3368075A1Fb3b3C511EdB1F
Facilitatorhttps://api.cdp.coinbase.com/platform/v2/x402
EIP-712 domainUSD 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

Server Config

{
  "mcpServers": {
    "x402-classifier": {
      "url": "https://web-production-2d1051.up.railway.app/sse"
    }
  }
}
Project Info
Created At
19 days ago
Updated At
15 days ago
Author Name
garyedgington
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

20 hours ago
Gpt Scrambler

2 days ago