Markup AI for AI agents
Markup AI runs content agents that check text against brand terminology, voice profiles, and style rules to improve writing quality. 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 Markup AI.
Run a style check on content
Run an agent against a draft to check it matches brand voice and terminology before publishing.
Search brand terminology
Search approved terminology to confirm a term is used correctly in a document, read-only.
Check an analysis profile's rules
Look up a workflow's analysis profile to understand what it checks before running it.
10 Markup AI actions, graded by risk.
Every Markup AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- markup_ai.get_agentGet Agent
- markup_ai.list_agentsList Agents
- markup_ai.get_workflowGet Workflow
- markup_ai.list_workflowsList Workflows
- markup_ai.search_terminologySearch Terminology
- markup_ai.get_analysis_profileGet Analysis Profile
- markup_ai.list_agent_categoriesList Agent Categories
- markup_ai.list_analysis_profilesList Analysis Profiles
- markup_ai.list_terminology_resourcesList Terminology Resources
write
1Create and change things. Allow, or ask the user first.
- markup_ai.run_agentRun Agent
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Markup AI in three steps.
- 01Your users connect Markup AIThey add their Markup AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “run Agent” can wait for the user to approve.
- 03Any agent can actYour agent calls Markup 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('markup_ai', { read: 'allow', write: 'ask', // run_agent destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Markup AI connects.
Users add their Markup 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 Markup 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 Markup AI from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Markup AI and Arc0, answered.
Can I use Markup AI with Claude, ChatGPT or Cursor?
Yes. Connect Markup 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 Markup AI actions you allow.
How do users connect Markup AI?
Users add their Markup 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 Markup AI actions can my agent take?
10 in total: 9 read, 1 write and 0 destructive, such as “run Agent”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Markup AI?
Yes. Allow read actions and deny writes in the Markup AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Markup AI too?
Yes. The same Markup AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Markup AI into your agent.
Your users connect Markup AI once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan