Enables the use of automated text classification and entity extraction within Make scenarios using the triage API.
Integrates with n8n workflows via HTTP nodes to provide structured JSON triage data for automated ticket and message processing.
Provides specialized processing for raw text from Slack messages to extract structured data like order IDs, contact info, and intent.
Allows Zapier automations to process unstructured text into guaranteed-schema JSON for routing and sentiment analysis.
A pay-per-call API that accepts raw unstructured text (emails, support tickets, Slack messages, voicemail transcripts) and returns a guaranteed-schema JSON triage object with intent, urgency, sentiment, entities, and routing.
curl -X POST https://your-domain.com/triage \
-H "Content-Type: application/json" \
-H "X-API-Key: sk_live_abc123" \
-d '{
"text": "Hi, I placed an order three days ago (order #8821) and still haven't received a shipping confirmation. This is really frustrating. Can someone help? - James, james@example.com",
"context": "ecommerce_support"
}'Response:
{
"schema_version": "v1",
"intent": "order_status_inquiry",
"urgency": "medium",
"sentiment": "frustrated",
"entities": {
"order_id": "8821",
"issue": "missing shipping confirmation",
"contact_name": "James",
"contact_email": "james@example.com",
"product": null,
"company": null,
"phone": null,
"date_mentioned": null
},
"suggested_routing": "order_fulfillment",
"summary": "Customer James reporting no shipping confirmation received 3 days after placing order #8821.",
"tags": ["order", "shipping", "delay"],
"confidence": 0.96,
"processing_time_ms": 312,
"model_used": "gpt-4o-mini"
}Related MCP server: Laya Agent Kit
git clone <repo-url> && cd intake-triage-api
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # fill in your keys
python main.pyMethod | Path | Auth | Description |
POST |
| API Key | Classify text and return triage JSON |
GET |
| None | Health check |
GET |
| None | Full JSON Schema of the output model |
GET |
| API Key | Current usage stats for your key |
POST |
| Admin Key | Create a new API key |
GET |
| None | Swagger UI |
Field | Type | Required | Description |
| string | Yes | Raw unstructured text to classify |
| string | No | Business context hint (e.g. |
| string | No |
|
Field | Type | Description |
|
| Response schema version |
| enum |
|
| enum |
|
| enum |
|
| object | Extracted entities: |
| enum |
|
| string | One-sentence summary |
| string[] | Lowercase keyword tags |
| float | 0.0–1.0 confidence score |
| int | Processing time in ms |
| string | LLM model used |
Pass your API key in the X-API-Key header with every request.
To get an API key, email api@yourdomain.com with your use case.
60 requests per minute per API key. Exceeding this returns 429.
Add to your Claude Desktop claude_desktop_config.json:
{
"mcpServers": {
"intake-triage": {
"url": "http://localhost:8001/sse"
}
}
}The MCP server exposes one tool: triage_text(text, context?) which returns the full triage JSON object.
Add an HTTP Request node
Set method to POST
URL: https://your-domain.com/triage
Headers: X-API-Key: your_key, Content-Type: application/json
Body (JSON): { "text": "{{ $json.message }}" }
The response JSON is directly usable in downstream nodes for routing
Use the HTTP module with the same POST configuration as above. The guaranteed JSON schema means you can map output fields directly without parsing.
Plan | Price | Calls/month |
Free | $0 | 500 |
Starter | $19/mo | 10,000 |
Agency | $99/mo | 100,000 |
RapidAPI: https://rapidapi.com/your-listing (coming soon)
Smithery: https://smithery.ai/your-listing (coming soon)
docker build -t intake-triage-api .
docker run -p 8000:8000 -p 8001:8001 --env-file .env intake-triage-apifly launch
fly secrets set OPENAI_API_KEY=sk-... ADMIN_KEY=...
fly deploypytest tests/ -vThis server cannot be deployed
Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key.
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Build and manage AI-native customer support agents from Claude or any MCP client.
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
