SEO MCP Server for Claude, ChatGPT and Cursor
Connect SERPclimber to the AI client you already work in. It reads your Search Console and GA4 evidence, your audit findings, your tasks, your backlink profile and your AI answer record. Through a two-step approval it can also file tasks, comment on them, change their status, and run a crawl or a backlink refresh.
replaces
- Exporting CSVs into a chat window
- Screenshotting dashboards for an agent
- Read-only SEO MCP servers
- Writing your own API glue
- 37 toolsreads and guarded writes# The same capabilities the in-product assistant uses.
- OAuth 2.1no API key to paste# Sign in, approve the scopes, revoke any client later.
- Two stepsbefore anything changes# Prepare a plan, then execute that exact plan.
- Remotenothing to install or host# One Streamable HTTP URL, hosted by us.
What SEO MCP Server does
Most SEO tools answer questions inside their own dashboard. An MCP server turns that around: your AI client asks the questions, and the tool answers with your real data.
SERPclimber publishes a remote Model Context Protocol server at /mcp. Point Claude, ChatGPT, Cursor, or anything else that speaks Streamable HTTP at that URL, sign in once, and your agent can work with the same picture of your site that the product has.
What makes this different from a read-only SEO MCP
Most SEO and AI-visibility MCP servers are report readers. They hand your agent a number and stop there, so the agent can tell you a page is losing clicks but cannot do anything about it.
This one can move the work forward. Alongside the read tools there is a small, deliberately narrow set of write tools, and every write goes through the same two-step plan-and-execute contract the product uses internally. Your agent proposes, SERPclimber freezes exactly what will happen, then the agent executes that frozen plan and nothing else.
A Google Search Console MCP, plus everything downstream of it
A generic Google Search Console MCP gives an agent clicks, impressions and positions. That is the raw material, not the work.
Because SERPclimber already joins Search Console with GA4, a site crawl, a backlink profile and AI answer checks, the same connection also exposes the audit findings, the task queue with its plans and measurements, the backlink profile with link targets, and the AI citation record. Your agent asks one question and gets the answer with the context attached.
How it works
- 1
Add one URL to your client
In Claude Code that is
claude mcp add --transport http serpclimber https://serpclimber.com/mcp. In ChatGPT, Claude Desktop or Cursor it is a custom connector or one entry inmcp.json. There is nothing to install and no key to generate. - 2
Sign in and approve the scopes
The client sends you to SERPclimber to sign in. You approve
mcpfor reads, andmcp:writeonly if you want the client to be able to spend or change anything. Approving takes seconds and does not require a paid plan. - 3
Ask in your own words
Your agent picks the right tools itself. "Which pages lost the most clicks this month and why" runs across Search Console analysis, page movement and the audit without you naming a single tool.
- 4
Let it prepare a change
When the agent wants to act it calls
actions_prepare. SERPclimber returns a plan listing the exact targets, the preconditions, the warnings, whether the change is reversible and when the plan expires. - 5
Execute the frozen plan
The agent calls
actions_executewith only that plan ID. Preconditions are re-checked at execution time, so a plan that has gone stale fails instead of doing something you did not agree to. - 6
Revoke whenever you like
Every connected client is listed in Settings with its scopes, connection date, last use and call count. Revoking invalidates all of that client's tokens immediately.
Your whole workspace, readable by your agent
The read tools mirror the product surfaces rather than exposing a raw API, so your agent gets answers in the shape a person would read them — ranked, diagnosed and already joined to the rest of your data.
- The project operating picture: stage, goal, open tasks and what needs you
- Performance evidence for the SEO, GA4, AI answers, Crawlers and Authority views
- Audit findings and the opportunity families with their numbers
- Task lanes, individual task threads, plans and measurements
- Backlinks: summary, link sources, referring domains, anchors, pages, and link targets
- AI answer questions, citations, competitors and crawler activity
- Reports, project settings, integration status, and the documentation itself
Writes are two calls, never one
An agent connected over MCP cannot send a direct mutation. That is a property of the server, not a setting you have to remember to switch on.
The first call, actions_prepare, produces a short-lived plan. The second, actions_execute, references only that plan ID. Plans are one-time, they expire, and their preconditions are checked again before anything runs — so the change that happens is the change you saw described.
- File a task draft, comment on a task, or change its status, owner or priority
- Run a site crawl or a backlink refresh
- Mark a directory listing submitted or not relevant
- Prepare a guided checklist for work you will do in your own stack
- Not available over MCP: creating, renaming or archiving projects, or binding integrations
Two scopes, and a client only gets what you approve
The mcp scope reads. The mcp:write scope additionally permits paid live services and the two-step action workflow. A client that only ever needs to answer questions never has to hold the write scope.
Neither scope is a way around the checks that already exist. Project ownership, subscription state, usage limits, integration health and workflow rules apply exactly as they do in the app — a call that fails one of them returns a readable error and the connection stays valid.
- Per-user and per-client authorisation, revocable one client at a time
- PKCE required; tokens are pinned to the exact MCP resource
- Dynamically registered clients are labelled unverified unless their metadata is published
- Credentials, encrypted fields and OAuth tokens are stripped from every response
SEO tools for Claude, ChatGPT and any MCP client
There is no per-client integration to wait for. The server implements the remote Streamable HTTP transport with OAuth discovery, which is what current MCP clients expect, so support is a function of the protocol rather than of our roadmap.
In practice that means Claude Code, Claude Desktop, claude.ai, ChatGPT connectors, Cursor and VS Code all connect the same way — and so will the next client, without us shipping anything.
- Claude Code, Claude Desktop and claude.ai
- ChatGPT custom connectors
- Cursor, VS Code and other `mcp.json` clients
- Any client speaking Streamable HTTP with OAuth discovery
Everything it covers
Remote Streamable HTTP server
One URL. Nothing to install, run or keep updated.
OAuth 2.1 with PKCE
No API keys copied into config files.
Dynamic client registration
New clients connect without us adding them first.
37 tools
The same capabilities the in-product assistant uses.
Project operating picture
Stage, goal, open tasks and what needs you, in one call.
Search Console analysis
Clicks, impressions, positions, page movement and topic clusters.
GA4 and crawler evidence
Traffic breakdowns and AI crawler activity for any window.
Audit findings and opportunities
What is wrong, what it is worth, and the numbers behind each family.
Task lanes and threads
List tasks by lane, read a task by number, see its plan and measurement.
Backlink profile
Summary, link sources, referring domains, backlinks, anchors, pages and link targets.
AI answer record
Questions, citations, competitors, and live engine asks with the write scope.
Reports and settings
Read generated reports, project settings and workspace defaults.
Documentation search
Your agent can read the manual before acting.
Two-step writes
Prepare a plan, then execute that exact plan.
Guarded task actions
File a task, comment, change status, owner or priority, or approve a waiting plan.
Crawl and backlink refresh
Start a site crawl or an authority refresh through a plan.
Expiring, one-time plans
Preconditions re-checked before execution.
Scope separation
`mcp` reads; `mcp:write` spends and changes.
Per-client revocation
Kill one client without touching the others.
Call telemetry
Scopes, connection date, last use and call totals per client.
Secret redaction
Credentials and tokens never appear in a response.
Is this the best MCP server for SEO?
That depends on what you want the agent to do. If you only need it to read AI-visibility numbers, several tools now publish an MCP server and any of them will answer that question.
The reason to use this one is that the same connection covers the whole workspace: search performance, traffic, backlinks, AI answers, the audit and the task queue. Your agent can read the finding, read the plan, comment on the task, and record progress, and every change goes through a plan you can read before it runs.
Frequently asked questions
No. Approving the OAuth connection is free. Individual tool calls still respect the same rules as the app, so a call that needs a subscription, a writable project, a connected integration or remaining usage returns a readable error such as subscription-required or usage-limit-reached. The connection itself stays valid.
Not in one step. Direct mutations are not available over MCP at all. A client must first call actions_prepare, which returns a plan describing the exact targets, warnings, reversibility and expiry, and then call actions_execute with only that plan ID. Preconditions are re-checked at execution. If you never approve the mcp:write scope, the client cannot reach those tools in the first place.
Deliberately quite a lot. MCP clients cannot create, rename, re-domain, archive or change your default project, and they cannot bind integrations. Anything that would change the shape of your workspace or touch credentials stays in the app. Possessing the write scope is not approval: an action that needs a person still waits for that person. Results never include credentials, encrypted fields or raw OAuth tokens.
Any client that supports remote MCP servers over Streamable HTTP with OAuth discovery. That currently includes Claude Code, Claude Desktop, claude.ai, ChatGPT custom connectors, Cursor and VS Code. Because the server implements the standard rather than per-client integrations, new clients tend to work without changes on our side.
An API expects you to write the glue: authenticate, page through endpoints, join the results, decide what matters. MCP hands the agent a described set of tools and lets it choose. You ask a question in your own words and the agent picks the calls. If you would rather write the glue yourself, the product surfaces are the same either way.
Open Settings → Account → MCP access. Every connected client is listed with its name, trust source, approved scopes, connection date, last use and call totals. Choosing Revoke invalidates every access and refresh token in that grant immediately. You can reconnect from the client if you revoke one by mistake.
Works with
~/serpclimber/conversationAI SEO Agent
Ask a general chatbot about your rankings and it will guess, because it has never seen your data. This assistant is pinned beside every page with the same context you have — your pages, your queries, your tasks, your backlinks and your AI answers — and it can act on what it finds, with your approval.
Read more~/serpclimber/settingsSEO Automation
Full autonomy is a big ask for something that edits your live site. SERPclimber runs one loop — audit, plan, approve, execute, verify, measure — and lets you decide how much of it runs without asking. Start with Copilot, where the engine does low-risk work on its own and asks before anything risky, external or paid.
Read more~/serpclimber/performance/seoSEO Dashboard
Search Console shows what ranks. GA4 shows what earns. Neither one shows you what to fix next. SERPclimber puts both on one timeline, adds AI answers, AI crawler activity and your backlink profile, and keeps 16 months of Search Console history so you can see a trend instead of a snapshot.
Read more~/serpclimber/performance/ai-answersAI Visibility
ChatGPT, Perplexity, Gemini, Claude and Google's AI Overviews answer questions about your market every day, citing somebody. AI visibility shows you which questions those are, who gets cited, and whether the AI crawlers can read your site at all.
Read morePoint it at your site.
A project takes one domain. The first pass tells you what it found — before anything changes on your site.