ConnectorX is a cloud MCP platform. Connect LINE, Gmail, GitHub and the rest of your stack once, and it aggregates their tools behind a single secure MCP URL for Claude, Cursor, or any AI agent — with per-connection permissions, write gates and metering built in.
$ claude mcp add --transport http connectorx https://mcp.connectorx.ai/mcp ✓ connectorx wired — sign in once, approve your connections ✓ 200+ tools ready: line_* gmail_* github_* zimbra_* … > reply to the LINE customer asking about opening hours → line_replyMessage · Shop OA · write gate open ✓ replied in 1.4s · logged to Activity
Answer the FAQ, take the booking, turn a chat order into a bill, nudge the lead that went quiet a week ago.
Voice-note a thought on the go, snap a receipt, ask “ยอดเดือนนี้เท่าไหร่” — and get a digest every morning at 7.
Triage overnight mail, draft replies in your voice, label and archive the noise before you've had coffee.
Issue the quotation, send the invoice, generate the official memo — number formats and forms done right.
Open the issue, paste the repro, comment the fix — and ping the shop-floor chat when CI goes red.
Read the live chart, run the screener, capture the setup for tomorrow's review — on your own desktop session.
One MCP endpoint aggregates every app you enable — multiple accounts included. Configure your agent once; new connections appear on its very next request. No local servers to install, update or babysit.
Desktop apps, CLIs and autonomous remote agents all run the same connections — each through an expiring surface scoped to exactly what that workflow needs, authorized by branded OAuth consent instead of pasted tokens.
Reads work from day one; sends, edits and broadcasts refuse until a human flips Allow writes. The gate is per connection, applies on the very next call, and revokes just as fast.
Customer messages, voice notes and photos arrive through a signed webhook inbox your agent can poll, download and answer — real conversations, not fire-and-forget notifications.
1,000 free tool calls a month on every plan, then flat per-call credits with an append-only ledger. Reserved before the call, refunded when it fails — agents can't surprise you.
Add each integration in the dashboard — credentials are AES-256-GCM encrypted at rest and never shown again in any UI or API. Multiple accounts per connector, each with its own permissions.
Add the endpoint as a custom connector in Claude for branded OAuth consent, or mint a scoped device token for CLIs and legacy clients.
Your agent sees every approved tool, namespaced per connector — line_replyMessage, gmail_send_message — with health, activity and usage tracked per call.
ConnectorX keeps the surface small: one hardened gateway between your tools and your agents, behind Cloudflare TLS. Credentials are AES-256-GCM encrypted before they ever touch the database, every call is scoped to the connection you approved, and the permission layer fails closed.
Health is reactive — a failure flags the connection, the next success heals it, and one-click Test probes stored credentials on demand.
connection: activeIf you choose to connect Gmail or Google Calendar, ConnectorX asks for your permission through Google's own consent screen, then accesses your Google account only to run the actions you or your AI agent explicitly request — reading, searching and labeling mail, checking your schedule, and (only after you open the per-connection write gate) sending email or creating and updating calendar events on your instruction.
Full details are in our Privacy Policy, including our adherence to the Google API Services User Data Policy and its Limited Use requirements.