Textcortex for AI agents
TextCortex generates and rewrites text with AI, covering product copy, social posts, emails, and translations for marketing and content teams. 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 Textcortex.
Draft a social media post
Generate a social post from a topic or product description for review before publishing.
Summarize a long document
Condense a long piece of text into a short summary for a quick read.
Draft an email for review
Write an email draft a person can edit and send themselves, rather than sending it automatically.
7 Textcortex actions, graded by risk.
Every Textcortex action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- textcortex.summarize_textSummarize Text
- textcortex.translate_textTranslate Text
write
5Create and change things. Allow, or ask the user first.
- textcortex.create_product_titleCreate Product Title
- textcortex.create_social_media_postCreate Social Media Post
- textcortex.create_video_descriptionCreate Video Description
- textcortex.generate_codeGenerate Code
- textcortex.generate_emailGenerate Email
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Textcortex in three steps.
- 01Your users connect TextcortexThey add their Textcortex api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Product Title” can wait for the user to approve.
- 03Any agent can actYour agent calls Textcortex through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('textcortex', { read: 'allow', write: 'ask', // create_product_title destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Textcortex connects.
Users add their Textcortex 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 Textcortex 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 Textcortex from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Textcortex and Arc0, answered.
Can I use Textcortex with Claude, ChatGPT or Cursor?
Yes. Connect Textcortex 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 Textcortex actions you allow.
How do users connect Textcortex?
Users add their Textcortex 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 Textcortex actions can my agent take?
7 in total: 2 read, 5 write and 0 destructive, such as “create Product Title”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Textcortex?
Yes. Allow read actions and deny writes in the Textcortex policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Textcortex too?
Yes. The same Textcortex connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Textcortex into your agent.
Your users connect Textcortex once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan