Rosette Text Analytics for AI agents
Rosette Text Analytics uses natural language processing to analyze text across hundreds of languages, matching names and addresses and identifying language. 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 Rosette Text Analytics.
Identify a document's language
Identify the language of an incoming message before routing it to the right support queue.
Match names across records
Compare name similarity between two records to check whether they refer to the same person.
Check for a duplicate address
Compare address similarity to flag possible duplicate customer records before merging them.
3 Rosette Text Analytics actions, graded by risk.
Every Rosette Text Analytics action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
3Create and change things. Allow, or ask the user first.
- rosette_text_analytics.name_similarityCompare Name Similarity
- rosette_text_analytics.address_similarityAddress Similarity
- rosette_text_analytics.language_identificationIdentify Language
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Rosette Text Analytics in three steps.
- 01Your users connect Rosette Text AnalyticsThey add their Rosette Text Analytics api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “compare Name Similarity” can wait for the user to approve.
- 03Any agent can actYour agent calls Rosette Text Analytics through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('rosette_text_analytics', { read: 'allow', write: 'ask', // name_similarity destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Rosette Text Analytics connects.
Users add their Rosette Text Analytics 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 Rosette Text Analytics 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 Rosette Text Analytics from any agent.
Rosette Text Analytics and Arc0, answered.
Can I use Rosette Text Analytics with Claude, ChatGPT or Cursor?
Yes. Connect Rosette Text Analytics 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 Rosette Text Analytics actions you allow.
How do users connect Rosette Text Analytics?
Users add their Rosette Text Analytics 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 Rosette Text Analytics actions can my agent take?
3 in total: 0 read, 3 write and 0 destructive, such as “compare Name Similarity”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Rosette Text Analytics?
Yes. Allow read actions and deny writes in the Rosette Text Analytics policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Rosette Text Analytics too?
Yes. The same Rosette Text Analytics connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Rosette Text Analytics into your agent.
Your users connect Rosette Text Analytics once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan