# Tisane Labs — how to use (mcp.ai)

Connect your Tisane Labs account and use 15 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Tisane Labs provides natural language processing APIs for content analysis, language detection, entity comparison, semantic similarity, text extraction, and translation.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_tisane?ms=1787291220000`
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. `tisane_analyze_text`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/tisane`
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/tisane/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/tisane/analyze/text` — Analyze text for sentiment, abuse, entities, topics, sentence structure, and other requested NLU details. Output sections vary with the text and settings.
  - body: { content: string, language: string, settings?: object }
- `POST https://api.mcp.ai/api/tisane/calculate/text/similarity` — Calculate semantic similarity between two same-language or cross-language text fragments. A result of -1 is an observed provider sentinel, not a normal 0-to-1 similarity score.
  - body: { settings?: object, first_text: string, second_text: string, first_language: string, second_language: string }
- `POST https://api.mcp.ai/api/tisane/compare/person/entities` — Compare two person-name entities, including cross-language names, and report whether Tisane considers them the same, different, or not single entities.
  - body: { first_entity: string, second_entity: string, first_language: string, second_language: string }
- `POST https://api.mcp.ai/api/tisane/detect/language` — Tool to detect the language of the provided text. Use when you need to identify the language code.
  - body: { text: string }
- `POST https://api.mcp.ai/api/tisane/detect/languages` — Detect one or more languages in text, optionally segmenting it, and return offsets plus provider-native integer confidence scores.
  - body: { content: string, delimiter?: string, language_hints?: string[] }
- `POST https://api.mcp.ai/api/tisane/extract/text` — Remove markup, scripts, styles, and JSON structure from UTF-8 text content and return the provider's raw cleaned text.
  - body: { content: string }
- `POST https://api.mcp.ai/api/tisane/get/family/details` — Tool to fetch metadata for a family from Tisane language models, including definition, description, hypernyms, and external references (Wikidata, WordNet). Use when you need detailed information about
  - body: { id: string }
- `POST https://api.mcp.ai/api/tisane/get/supported/languages` — Tool to list all languages supported by the API. Use when needing to discover available languages for text analysis or processing. Call before submitting text to ensure support.
- `POST https://api.mcp.ai/api/tisane/list/feature/values` — Tool to list feature values for a particular category such as entity types, subtypes, abuse types, and tags. Use when you need to discover valid values for a specific feature category before analysis 
  - body: { type: string, language: string, description: string }
- `POST https://api.mcp.ai/api/tisane/list/hypernyms` — Tool to list all hypernyms related to a family. A hypernym is a parent concept (e.g., vehicle is a hypernym of truck). Use when you need to understand the conceptual hierarchy or broader categories fo
  - body: { family: string, maxLevel: string }
- `POST https://api.mcp.ai/api/tisane/list/hyponyms` — Tool to list all hyponyms related to a family. A hyponym is a child concept (e.g., 'truck' is a hyponym of 'vehicle'). Use when you need to discover more specific concepts within a semantic family.
  - body: { family: string, maxLevel: string }
- `POST https://api.mcp.ai/api/tisane/list/inflections` — Tool to retrieve inflected forms of a specified lexeme within a given language family. Use when you need to get all grammatical variants of a word.
  - body: { family: string, lexeme: string, language: string }
- `POST https://api.mcp.ai/api/tisane/list/languages` — List Tisane language records and whether each language model is currently loaded.
- `POST https://api.mcp.ai/api/tisane/list/word/senses` — Tool to fetch all senses (meanings) related to a word. Use when you need to explore word definitions, families, features, and lemma information for linguistic analysis.
  - body: { word: string, language: string }
- `POST https://api.mcp.ai/api/tisane/transform/text` — Translate text to another language, or paraphrase it by using the same source and target language. Returns the provider's raw transformed text.
  - body: { content: string, settings?: object, source_language: string, target_language: string }

## Example prompts
- "What can I do in Tisane Labs?"
- "Show me a summary of my Tisane Labs account"

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