Integration

Tisane integration

Tisane is a natural language understanding API for content moderation and text analytics in 35 languages. Analyze a text to flag problematic content (personal attacks, bigotry, profanity, sexual advances, criminal activity, attempts to move a conversation to outside contacts, signs of mental health issues, spam and more) with a severity, and extract sentiment, named entities and topics; detect which languages a text is written in; translate or paraphrase a text; compare two person names; and list the inflected forms of a word. The markup clean-up helper and the semantic similarity score (a bare number, which the platform cannot return as fields) are not exposed. Authentication is a subscription key from the Tisane developer portal, sent in the Ocp-Apim-Subscription-Key header.

Connect Tisane How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Tisane.Built from the 6 Tisane tools below, on the connection you add once.

What you can do with Tisane

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Language, 2 operations

detect_languageDetect languagePOSTDetects the language of a text and returns a breakdown by fragment: each entry gives the language code, where the fragment starts and how long it is, and a confidence score.
list_languagesList languagesGETLists the languages Tisane supports, with each language's code (pass it as language to analyze_text or as from and to on translate_text), native and English names, and whether it is written right to left.

Text, 2 operations

analyze_textAnalyze textPOSTAnalyzes a text and returns what Tisane found in it: problematic content in abuse (type such as personal_attack, bigotry, profanity, sexual_advances, criminal_activity, external_contact, mental_issues or spam, with a severity from low to extreme).
translate_textTranslate textPOSTTranslates a text into another language, or paraphrases it when the source and target languages are the same. Tisane also handles slang, jargon and obfuscated wording. Set from to * to let Tisane detect the source language.

Inflection, 1 operation

list_inflectionsList inflectionsGETLists the inflected forms of one word (lexeme) of a language: each form with its grammatical features, and which form is the dictionary form (lemma). The lexeme and family ids come from analyze_text run with the words setting on.

Person name, 1 operation

compare_entitiesCompare entitiesPOSTCompares two person names, possibly written in different languages, and says whether they refer to the same person: result is same (identical, the name order may differ).

Use Tisane from Claude Code, Cursor or Codex

Connect Tisane in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Tisane operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Tisane

Create your workspace
Sign up free. Nothing to install.
Connect Tisane once
Add your Tisane connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.