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.
What agents do in Tisane Labs.
Detect the language of a text
Identify what language a piece of text is written in before routing it.
Analyze text for entities and sentiment
Run a passage of text through analysis to extract entities and tone, a read-only lookup.
Compare two person entities
Check whether two mentioned names likely refer to the same person.
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
14Look things up. Allowed by default.
- tisane_labs.list_hyponymsList Hyponyms
- tisane_labs.list_hypernymsList Hypernyms
- tisane_labs.list_languagesList Supported Languages
- tisane_labs.list_inflectionsList Inflections
- tisane_labs.list_word_sensesList Word Senses
- tisane_labs.get_family_detailsGet Family Details
- tisane_labs.list_feature_valuesList Feature Values
- tisane_labs.get_supported_languagesGet Supported Languages
- tisane_labs.analyze_textAnalyze Text
- tisane_labs.extract_textExtract Text
- tisane_labs.detect_languageDetect Language
- tisane_labs.detect_languagesDetect Languages
- tisane_labs.compare_person_entitiesCompare Person Entities
- tisane_labs.calculate_text_similarityCalculate Text Similarity
write
1Create and change things. Allow, or ask the user first.
- tisane_labs.transform_textTransform Text
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Tisane Labs in three steps.
- 01Your users connect Tisane LabsThey add their Tisane Labs api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “transform Text” can wait for the user to approve.
- 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.
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
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
Use Tisane Labs from any agent.
Tisane Labs and Arc0, answered.
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.
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.
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.
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.
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.
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