Mintlify for AI agents

Mintlify is a documentation platform teams use to publish developer docs, with an admin API to trigger deployments and pull analytics. 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.

Developer toolsAPI keyMCP + RESTmintlify.com
AUDIT LOG · MINTLIFYPOLICY: acme-support
09:41:07 · claude · u_8f2read
mintlify.get_feedback
Get Feedback✓ allowed · 212ms
09:41:08 · claude · u_8f2read
mintlify.get_agent_job
Get Agent Job✓ allowed · 164ms
09:41:09 · claude · u_8f2write
mintlify.create_agent_job
Create Agent Job✓ approved · approved by user
EVERY MINTLIFY CALL, ON THE RECORD
01 · USE CASES

What agents do in Mintlify.

01

Check docs page analytics

Pull page views and search queries for a documentation site over a period, read-only.

02

Trigger a docs preview

Trigger a preview build of updated docs content before it goes live.

03

Approve before triggering an update

Require approval before triggering a full docs update, since it publishes changes to the live site.

02 · ACTIONS

14 Mintlify actions, graded by risk.

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

read

9

Look things up. Allowed by default.

  • mintlify.get_feedback
    Get Feedback
  • mintlify.get_agent_job
    Get Agent Job
  • mintlify.get_page_views
    Get Page Views
  • mintlify.get_update_status
    Get Update Status
  • mintlify.get_search_queries
    Get Search Queries
  • mintlify.get_unique_visitors
    Get Unique Visitors
  • mintlify.get_feedback_by_page
    Get Feedback By Page
  • mintlify.get_assistant_caller_stats
    Get Assistant Caller Stats
  • mintlify.get_assistant_conversations
    Get Assistant Conversations

write

5

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

  • mintlify.create_agent_job
    Create Agent Job
  • mintlify.send_agent_message
    Send Agent Message
  • mintlify.trigger_update
    Trigger Update
  • mintlify.trigger_preview
    Trigger Preview
  • mintlify.trigger_automation
    Trigger Automation

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Mintlify in three steps.

  1. 01Your users connect MintlifyThey add their Mintlify api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Agent Job” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Mintlify 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('mintlify', {
  read: 'allow',
  write: 'ask',        // create_agent_job
  destructive: 'deny',  
})

# 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 Mintlify connects.

Users add their Mintlify 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 Mintlify 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 Mintlify from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Mintlify and Arc0, answered.

Q01

Can I use Mintlify with Claude, ChatGPT or Cursor?

Yes. Connect Mintlify 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 Mintlify actions you allow.

Q02

How do users connect Mintlify?

Users add their Mintlify 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 Mintlify actions can my agent take?

14 in total: 9 read, 5 write and 0 destructive, such as “create Agent Job”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Mintlify?

Yes. Allow read actions and deny writes in the Mintlify policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Mintlify too?

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

Get started

Plug Mintlify into your agent.

Your users connect Mintlify once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

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