Attio MCP: The Official Server and What It Can Do
Yes — Attio has an official MCP server. It’s a hosted, remote server at mcp.attio.com/mcp that lets any MCP-compatible AI tool read and write your CRM — people, companies, deals, tasks, notes, and lists — through a one-time OAuth login, no API keys and no code. It’s available on all Attio plans and for all workspace members. So if you’re searching “Attio MCP,” the connection you want is real and built by Attio itself.
The thing worth knowing before you set it up: an MCP server hands your CRM to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches Attio for you, nothing fires when a deal changes stage, and nothing runs while the chat is closed. Here’s exactly what the Attio MCP does, how to turn it on, where it stops — and what to use when you want Attio work that runs on its own.
See also: the full MCP server list — which apps have one, and what each can reach.
What the Attio MCP server does
Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Cursor, and others — talk to an outside app through a shared interface. Attio maintains an official hosted server at mcp.attio.com/mcp, and it authenticates you as your own Attio user, so the AI gets exactly the permissions your account already has: reads are auto-approved, and writes ask for confirmation before they touch your data.
With it connected, an AI client can:
- Look up records — “pull the Acme deal and everyone associated with it” answered from the live workspace, across people, companies, deals, and lists.
- Query and filter — “which deals in the pipeline have no next task?” run against real CRM data instead of a guess.
- Create and update — add a person, move a deal stage, log a note, or create a task without opening Attio.
- Reason across objects — summarize a pipeline, spot stalled deals, and draft follow-ups from the actual notes, tasks, and activity on a record.
It’s genuinely useful for ad-hoc work: ask a question, get an answer grounded in your CRM, make a change on the spot. This is the honest core of any Attio AI integration built on MCP.
How to set up the Attio MCP server
The remote server is the quick path — no code, no hosting:
- In your AI client’s connector settings, add a remote MCP server pointing at
https://mcp.attio.com/mcp. - Authorize it against your Attio workspace through the OAuth prompt — you’re granting the AI the same scopes your user has, and you can revoke the session from Attio’s settings later.
- Confirm the tools appear in the client, then start a chat and ask it to read or update a record.
In Claude Code the same thing is one line — claude mcp add --transport http attio https://mcp.attio.com/mcp, then /mcp to finish the OAuth login. Claude Desktop, Claude.ai, ChatGPT, and Cursor each have their own “add a remote MCP server” screen that points at the same URL. Attio’s MCP docs cover the per-client steps.
Where the Attio MCP stops
None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:
- It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch Attio; it waits for you to ask.
- No triggers. A deal moving to Won, a new person added to a list, a task going overdue — none of these can start anything through MCP. There’s no “when this happens in Attio, do that.”
- It’s one app at a time. The Attio MCP knows Attio. Getting a won deal into Stripe, a Slack channel, and a Google Sheet means wiring up (and authing) a separate MCP server for each, then hoping your client can juggle them in one turn.
- You own the plumbing and the scopes. The OAuth session, and the blast radius of read/write access to your CRM, are on you — a write tool acts as your Attio user, with only that per-write confirmation between it and your data.
So the Attio MCP is a great way to ask Attio things and make one-off edits. It is not a way to make Attio run — to have work happen on a schedule or in reaction to an event, across the other tools a deal touches.
Running Attio work that doesn’t need a chat open
That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to Attio natively — no MCP server to host, no OAuth plumbing to maintain — and to the ~260 other apps it supports natively, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so Attio work happens whether or not anyone has a chat window open.
A few things that MCP can’t do but a Carly workflow can:
- When a deal hits Won → create the Stripe customer, post to the
#winsSlack channel, and add a row to the finance sheet — automatically, the moment it happens. - Every morning → summarize deals with no task or activity in 7 days and send the list to the owner.
- When a person is added to a list → enrich the record, assign a follow-up task, and draft the first outreach email for approval.
The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the Attio connection and everything downstream.
If you just want to interrogate your CRM from a chat, Attio’s official MCP server is the right tool and it’s free to connect. If you want Attio to actually do things — on a trigger, on a schedule, across every app a deal flows through — that’s the job MCP wasn’t built for, and it’s the one Carly was.
FAQ
Does Attio have an official MCP server?
Yes. Attio ships a hosted remote MCP server at mcp.attio.com/mcp that gives MCP-compatible AI tools read and write access to your CRM — people, companies, deals, tasks, notes, and lists. It uses OAuth (no API keys) and is available on all Attio plans.
Is the Attio MCP server free? Connecting it is free and available to all workspace members; you’re authorizing an AI client against your existing Attio account and permissions. You still need whatever Attio plan your data lives on.
Can the Attio MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven Attio work across apps, you need a workflow tool like Carly rather than an MCP server.
Can I connect Attio to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to Attio for you and lets you build the automation in plain language — describe what you want to happen and it wires up the CRM and the other apps involved, with no server to host and no code to write.
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
