Ahrefs MCP Server: What It Does and How to Connect Ahrefs to AI in 2026
Yes — Ahrefs has an official MCP server. It’s a hosted remote server at api.ahrefs.com/mcp/mcp, and it lets any MCP-compatible AI tool pull live Site Explorer, Keywords Explorer, Rank Tracker, and Site Audit data straight from your Ahrefs account. So if you’re searching “Ahrefs MCP,” the connection you want already exists — no third-party workaround needed.
The thing worth knowing before you set it up: an MCP server hands your SEO data to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches your rankings for you, nothing fires when a competitor gains backlinks, and nothing runs while the chat is closed. Here’s exactly what the Ahrefs MCP does, how to turn it on, where it stops — and what to use when you want Ahrefs work that runs on its own.
What the Ahrefs MCP server does
Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Copilot, Cursor, and others — talk to an outside app through a shared interface. Ahrefs’ official remote server exposes over 100 tools across its core products, so once connected, an AI client can:
- Pull backlink data — comprehensive backlink stats, referring domains, and broken backlinks for any site via Site Explorer.
- Research keywords — search volume, historical trends, and related terms straight from Ahrefs’ keyword database.
- Check rankings — a summary of keyword positions and visibility from Rank Tracker.
- Run batch analysis — SEO metrics across up to 100 URLs or domains at once, and pull Site Audit project results.
It’s genuinely useful for ad-hoc research: ask a question, get an answer grounded in your actual Ahrefs data, no exporting a CSV or flipping between tabs. Worth noting: the tools are almost entirely read operations — they retrieve data rather than create or change anything in your Ahrefs account.
How to set up the Ahrefs MCP server
The remote server is the only supported path — Ahrefs retired its old local MCP server, which is no longer maintained:
- In your AI client’s connector settings, add a remote MCP server pointing at
https://api.ahrefs.com/mcp/mcp. - Authorize it through the OAuth prompt using an Ahrefs API key with MCP scope (a separate scope from a standard API key) — your first connection opens a browser window to sign in.
- Confirm the tools appear in the client, then start a chat and ask it to pull a keyword or backlink report.
MCP access requires a paid Ahrefs plan — Lite and up — with data limits that scale by tier: Lite caps responses at 100 rows per request, Enterprise is unlimited. Every MCP call also draws from your plan’s API unit allowance, same as Ahrefs’ regular API.
Where the Ahrefs 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 your rankings; it waits for you to ask.
- No triggers. A competitor picking up 50 new referring domains, a keyword dropping out of the top 10, a Site Audit finding a spike in broken links — none of these can start anything through MCP. There’s no “when this happens in Ahrefs, do that.”
- It’s one app at a time. The Ahrefs MCP knows Ahrefs. Getting a ranking drop into a Slack alert, a content brief in Google Docs, and a task on your editorial calendar 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 MCP-scoped API key, its unit consumption, and the blast radius of what it can see are all on you.
So the Ahrefs MCP is a great way to ask Ahrefs things and get a grounded answer fast. It is not a way to make Ahrefs data run — to have work happen on a schedule or in reaction to a ranking change, across the other tools your SEO workflow touches.
Running Ahrefs work that doesn’t need a chat open
That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to Ahrefs through your own API key — no MCP server to configure, no separate OAuth scope to manage — and to the ~260 other apps it supports natively, plus anything else with a public API. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so Ahrefs data gets acted on whether or not anyone has a chat window open.
A few things that MCP can’t do but a Carly workflow can:
- Every Monday morning → pull this week’s Rank Tracker movement, summarize the biggest gains and losses, and email the list to the team.
- When a tracked keyword drops out of the top 10 → alert the
#seoSlack channel and add the page to a content-refresh task list. - Monthly → run batch analysis on your top competitors’ domains, draft a summary of new backlink activity, and drop it into a Google Doc for review.
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 Ahrefs connection and everything downstream.
If you just want to interrogate your SEO data from a chat, Ahrefs’ official MCP server is the right tool. If you want that data to actually do things — on a trigger, on a schedule, across every app your content workflow touches — that’s the job MCP wasn’t built for, and it’s the one Carly was.
FAQ
Does Ahrefs have an official MCP server?
Yes. Ahrefs runs a hosted remote MCP server at api.ahrefs.com/mcp/mcp that exposes Site Explorer, Keywords Explorer, Rank Tracker, and Site Audit data to any MCP-compatible AI client. Its older local MCP server is deprecated and no longer maintained.
Is the Ahrefs MCP server free? No — it requires a paid Ahrefs plan (Lite or higher), and each MCP call draws from your plan’s API unit allowance. There’s no extra charge on top of your subscription, but the free/trial tier doesn’t include MCP access.
Can the Ahrefs 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 scheduled reports or alerts on ranking and backlink changes, you need a workflow tool like Carly rather than an MCP server.
What AI tools can connect to Ahrefs over MCP? Any MCP-compatible client, including Claude, ChatGPT, Copilot, Cursor, and platforms like n8n and Lovable, can connect to the Ahrefs MCP server, though each platform may have its own setup steps.
Can I connect Ahrefs to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to Ahrefs for you and lets you build the automation in plain language — describe what you want to happen and it wires up Ahrefs 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."
