Linguin AI for AI agents
Linguin AI detects the language of text and scores English content for profanity through a direct API, used to screen user-generated content. 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 Linguin AI.
Detect a message's language
Detect the language of an incoming message before routing it to the right support queue.
Screen text for profanity
Check a piece of user-submitted text for profanity before it is published, a read-only check.
Batch-check a list of comments
Run a batch of comments through profanity checking to flag which ones need moderator review.
6 Linguin AI actions, graded by risk.
Every Linguin AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- linguin_ai.get_account_statusGet Account Status
- linguin_ai.list_supported_languagesList Supported Languages
- linguin_ai.check_profanityCheck Profanity
- linguin_ai.detect_languageDetect Language
- linguin_ai.check_profanity_batchCheck Profanity in Batch
- linguin_ai.detect_languages_batchDetect Languages in Batch
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Linguin AI in three steps.
- 01Your users connect Linguin AIThey add their Linguin AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Linguin AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('linguin_ai', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Linguin AI connects.
Users add their Linguin AI 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 Linguin AI 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 Linguin AI from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Linguin AI and Arc0, answered.
Can I use Linguin AI with Claude, ChatGPT or Cursor?
Yes. Connect Linguin AI 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 Linguin AI actions you allow.
How do users connect Linguin AI?
Users add their Linguin AI 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 Linguin AI actions can my agent take?
6 in total: 6 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Linguin AI?
Yes. Allow read actions and deny writes in the Linguin AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Linguin AI too?
Yes. The same Linguin AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Linguin AI into your agent.
Your users connect Linguin AI once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan