Connect
once.
Every agent gets
exactly the right tools.
One work Sentry, one personal Sentry — connected once. Claude, Claude Code, Codex, Cursor, and Hermes all reuse them, each with its own rules. No re-auth. No over-sharing.
Per tool. Per account. Per agent.
Not one big OAuth grant. Codex gets the work Linear and nothing else. Claude Code gets both Sentries. Hermes can read everything but writes nothing without a tap from you.
Three steps. Then you never think about it again.
Connect accounts
OAuth into Linear, Sentry, Notion, PostHog — or paste any MCP URL. Work, personal, side project: as many accounts per integration as you live in.
Scope every agent
The same connections, reused by every agent — but each one sees only what you flip on. Change your mind? Flip it back. Nothing re-authenticates.
Paste one URL
Each agent is a scoped MCP endpoint or a key-protected OpenAPI. Drop it into Claude, Claude Code, Codex, Hermes — or your own backend.
One permission layer.
Three ways in.
Test in AIP Chat
Talk to your connected tools right in the dashboard. Approve or reject risky calls inline before wiring anything up.
dash.aipx.run/chat
A scoped MCP endpoint
One URL per agent. Claude, Claude Code, Codex, Cursor — anything that speaks MCP gets only the tools you flipped on.
https://dash.aipx.run/mcp/:agent
A key-protected API
A generated OpenAPI document plus an agent key. Call approved tools from Hermes or any backend, no MCP required.
GET /api/agents/:agent/openapi
Simple. Counted in accounts,
not in seats.
Agents, integrations, tool calls, audit — unlimited on every plan. You only ever pay for connected accounts.
- Up to 10 connected accounts
- Unlimited agents and tool calls
- Every integration, full audit trail
- Unlimited connected accounts
- Everything in Free
- Cancel anytime
Stop re-connecting
the same five tools.
Connect them once, scope your agents, and get back to work. Free while in beta.