Windsor.ai for AI agents
Windsor.ai connects marketing data sources for unified reporting, used by marketing and analytics teams that report across many ad platforms at once. 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 Windsor.ai.
Query connector data
Pull marketing performance data from a connected source, a read-only query.
List available connectors
Check which data sources are connected before building a report.
List connector fields
Check which fields a connector exposes before including it in a report.
6 Windsor.ai actions, graded by risk.
Every Windsor.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- windsor_ai.list_connectorsList Connectors
- windsor_ai.query_connector_dataQuery Connector Data
- windsor_ai.list_connector_fieldsList Connector Fields
- windsor_ai.list_connector_actionsList Connector Actions
- windsor_ai.list_connector_optionsList Connector Options
- windsor_ai.list_co_user_linked_accountsList Co-User Linked Accounts
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Windsor.ai in three steps.
- 01Your users connect Windsor.aiThey add their Windsor.ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Windsor.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('windsor_ai', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Windsor.ai connects.
Users add their Windsor.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 Windsor.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 Windsor.ai from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Windsor.ai and Arc0, answered.
Can I use Windsor.ai with Claude, ChatGPT or Cursor?
Yes. Connect Windsor.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 Windsor.ai actions you allow.
How do users connect Windsor.ai?
Users add their Windsor.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 Windsor.ai actions can my agent take?
6 in total: 6 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Windsor.ai?
Yes. Allow read actions and deny writes in the Windsor.ai policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Windsor.ai too?
Yes. The same Windsor.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Windsor.ai into your agent.
Your users connect Windsor.ai once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan