Tisane Labs for AI agents

Tisane Labs offers natural language processing for content analysis, including language detection, entity comparison, and translation, used by teams building text-heavy features. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

AI and modelsAPI keyMCP + RESTtisane.ai
AUDIT LOG · TISANE LABSPOLICY: acme-support
09:41:07 · claude · u_8f2read
tisane_labs.list_hyponyms
List Hyponyms✓ allowed · 212ms
09:41:08 · claude · u_8f2read
tisane_labs.analyze_text
Analyze Text✓ allowed · 164ms
09:41:09 · claude · u_8f2write
tisane_labs.transform_text
Transform Text✓ approved · approved by user
EVERY TISANE LABS CALL, ON THE RECORD
01 · USE CASES

What agents do in Tisane Labs.

01

Detect the language of a text

Identify what language a piece of text is written in before routing it.

02

Analyze text for entities and sentiment

Run a passage of text through analysis to extract entities and tone, a read-only lookup.

03

Compare two person entities

Check whether two mentioned names likely refer to the same person.

02 · ACTIONS

15 Tisane Labs actions, graded by risk.

Every Tisane Labs action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

14

Look things up. Allowed by default.

  • tisane_labs.list_hyponyms
    List Hyponyms
  • tisane_labs.list_hypernyms
    List Hypernyms
  • tisane_labs.list_languages
    List Supported Languages
  • tisane_labs.list_inflections
    List Inflections
  • tisane_labs.list_word_senses
    List Word Senses
  • tisane_labs.get_family_details
    Get Family Details
  • tisane_labs.list_feature_values
    List Feature Values
  • tisane_labs.get_supported_languages
    Get Supported Languages
  • tisane_labs.analyze_text
    Analyze Text
  • tisane_labs.extract_text
    Extract Text
  • tisane_labs.detect_language
    Detect Language
  • tisane_labs.detect_languages
    Detect Languages
  • tisane_labs.compare_person_entities
    Compare Person Entities
  • tisane_labs.calculate_text_similarity
    Calculate Text Similarity

write

1

Create and change things. Allow, or ask the user first.

  • tisane_labs.transform_text
    Transform Text

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Tisane Labs in three steps.

  1. 01Your users connect Tisane LabsThey add their Tisane Labs api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “transform Text” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Tisane Labs through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('tisane_labs', {
  read: 'allow',
  write: 'ask',        // transform_text
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Tisane Labs connects.

Users add their Tisane Labs api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Tisane Labs connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Tisane Labs from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Tisane Labs and Arc0, answered.

Q01

Can I use Tisane Labs with Claude, ChatGPT or Cursor?

Yes. Connect Tisane Labs to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Tisane Labs actions you allow.

Q02

How do users connect Tisane Labs?

Users add their Tisane Labs api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Tisane Labs actions can my agent take?

15 in total: 14 read, 1 write and 0 destructive, such as “transform Text”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Tisane Labs?

Yes. Allow read actions and deny writes in the Tisane Labs policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Tisane Labs too?

Yes. The same Tisane Labs connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Tisane Labs into your agent.

Your users connect Tisane Labs once, under your brand. Your agent gets 15 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan