Read AI for AI agents
Read AI retrieves meeting transcripts, summaries, action items, and metrics, and can deploy meeting agents. Teams use it to capture and share what happened in a meeting without manual notes. 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 Read AI.
Get a meeting's summary
Retrieve the summary and action items from a completed meeting for follow-up.
Check recent meetings read-only
List recent meetings to find the one that needs a report shared.
Share a meeting report with approval
Share a meeting report externally only after the organizer confirms it is appropriate to send.
4 Read AI actions, graded by risk.
Every Read AI 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.
- read_ai.list_meetingsList meetings
- read_ai.get_meeting_by_idGet meeting by
write
2Create and change things. Allow, or ask the user first.
- read_ai.create_meeting_agentCreate meeting agent
- read_ai.share_meeting_reportShare meeting report
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Read AI in three steps.
- 01Your users connect Read AIThey sign in to Read AI on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, and writes like “create meeting agent” can wait for the user to approve.
- 03Any agent can actYour agent calls Read 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('read_ai', { read: 'allow', write: 'ask', // create_meeting_agent destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Read AI connects.
Read AI runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Read AI through the same endpoint, policies and audit log as every other app.
The same Read 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
- OAuth 2.0 (MCP)
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Read AI from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Read AI and Arc0, answered.
Can I use Read AI with Claude, ChatGPT or Cursor?
Yes. Connect Read 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 Read AI actions you allow.
How do users connect Read AI?
Read AI runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Read AI through the same endpoint, policies and audit log as every other app.
Which Read AI actions can my agent take?
4 in total: 2 read, 2 write and 0 destructive, such as “create meeting agent”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Read AI?
Yes. Allow read actions and deny writes in the Read AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Read AI too?
Yes. The same Read AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Read AI into your agent.
Your users connect Read AI once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan