Get started

Metatextai for AI agents

Metatext AI specializes in natural language processing, helping teams automate text generation, sentiment analysis, and content moderation guardrails for their applications. 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.

Connect MetatextaiSee the 13 actions ↓
AI and modelsAPI keyMCP + RESTmetatext.ai
AUDIT LOG · METATEXTAIPOLICY: acme-support
09:41:07 · claude · u_8f2read
metatextai.list_models
List Models✓ allowed · 212ms
09:41:08 · claude · u_8f2read
metatextai.extract
Run Extraction✓ allowed · 164ms
09:41:09 · claude · u_8f2write
metatextai.create_policy_guardrails
Create Policy Guardrails✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
metatextai.delete_policy_guardrails
Delete Guardrail Policy✕ blocked · policy: deny
EVERY METATEXTAI CALL, ON THE RECORD
01 · USE CASES

What agents do in Metatextai.

01

Classify a piece of text

Classify a submitted text into categories, such as sentiment, for a moderation workflow.

02

Screen a message against guardrails

Evaluate a message against a guardrail policy before it is sent to a model or user.

03

Approve before deleting a policy

Require approval before deleting a guardrail policy, since it removes active content protection.

02 · ACTIONS

13 Metatextai actions, graded by risk.

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

read

5

Look things up. Allowed by default.

  • metatextai.list_models
    List Models
  • metatextai.list_applications
    List Applications
  • metatextai.list_policies_guardrails
    List Guardrail Policies
  • metatextai.list_red_team_test_probes
    List Red Team Test Probes
  • metatextai.extract
    Run Extraction

write

7

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

  • metatextai.create_policy_guardrails
    Create Policy Guardrails
  • metatextai.update_policy_guardrails
    Update Policy Guardrails
  • metatextai.classify
    Classify Text
  • metatextai.evaluate
    Evaluate Messages
  • metatextai.generate
    Generate Text
  • metatextai.chat_completions
    Chat Completions
  • metatextai.run_red_team_test_scan
    Run Red Team Test Scan

destructive

1

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

  • metatextai.delete_policy_guardrails
    Delete Guardrail Policy
03 · HOW IT WORKS

Metatextai in three steps.

  1. 01Your users connect MetatextaiThey add their Metatextai api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Policy Guardrails” can wait for the user, and “delete Guardrail Policy” can be denied outright.
  3. 03Any agent can actYour agent calls Metatextai 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('metatextai', {
  read: 'allow',
  write: 'ask',        // create_policy_guardrails
  destructive: 'deny',  // delete_policy_guardrails
})

# 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 Metatextai connects.

Users add their Metatextai 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 Metatextai 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 Metatextai from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Metatextai and Arc0, answered.

Q01

Can I use Metatextai with Claude, ChatGPT or Cursor?

Yes. Connect Metatextai 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 Metatextai actions you allow.

Q02

How do users connect Metatextai?

Users add their Metatextai 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 Metatextai actions can my agent take?

13 in total: 5 read, 7 write and 1 destructive, such as “create Policy Guardrails”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Metatextai?

Yes. Actions like “delete Guardrail Policy” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Metatextai too?

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

Get started

Plug Metatextai into your agent.

Your users connect Metatextai once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.

Connect MetatextaiBrowse all apps →

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