# Rosette Text Analytics — how to use (mcp.ai)

Connect your Rosette Text Analytics account and use 3 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Rosette Text Analytics is a platform that uses natural language processing, statistical modeling, and machine learning to analyze unstructured and semi-structured text across 364 language-encoding-script combinations, revealing valuable information and actionable data.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_rosette_text_analytics?ms=1787295900000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `rosette_text_analytics_address_similarity`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/rosette_text_analytics`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/rosette_text_analytics/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/rosette_text_analytics/address/similarity` — Compares two addresses and returns a similarity score. Addresses can be provided as single strings or as structured objects. The tool is optimized for English, Simplified Chinese, and Traditional Chin
  - body: { address1: object, address2: object }
- `POST https://api.mcp.ai/api/rosette_text_analytics/language/identification` — This tool identifies the natural language of a given text. It takes a string of text as input and returns the detected language along with a confidence score. Optional parameters include specifying a 
  - body: { content?: string, contentUri?: string, multilingual?: boolean, koreanDialects?: boolean }
- `POST https://api.mcp.ai/api/rosette_text_analytics/name/similarity` — The 'Name Similarity' tool compares two entity names (Person, Location, or Organization) and returns a similarity score between 0 and 1 to indicate if the names are similar. It is useful for tasks suc
  - body: { name1: object, name2: object }

## Example prompts
- "What can I do in Rosette Text Analytics?"
- "Show me a summary of my Rosette Text Analytics account"

## More
- Page: https://mcp.ai/rosette_text_analytics
- Agent spec (llms.txt): https://mcp.ai/rosette_text_analytics/llms.txt
- Postman collection: https://mcp.ai/rosette_text_analytics/postman.json