MCP ServerHTTP

OpenSEO MCP Server

OpenSEO provides a remote MCP at app.openseo.so/mcp (streamable HTTP) that exposes its SEO research platform to an AI model as tools: keyword metrics, live Google SERPs, competitor comparisons, rank tracking, backlink data and Google Search Console performance. The first connection runs through OpenSEO login via OAuth; headless clients can use a personal API key instead.

Try OpenSEO in Agent Studio OpenSEO MCP documentation

Hosted URL

https://app.openseo.so/mcp

Suggested model

Claude Sonnet 4.5

Chat with 60+ AI models on the same workflow — switch to a different model mid-conversation and re-run the same prompt, or use Compare mode to put several side-by-side and balance quality vs. cost.

Auth

OAuth by default — the first connection sends you through OpenSEO login. For headless clients, create a personal API key under Settings → API keys and send it as a bearer token.

What the OpenSEO MCP server does

How models use it and what it is built for.

The OpenSEO MCP is aimed at anyone who currently does SEO research by pivoting between a keyword tool, a SERP checker and Search Console. Instead of exporting three CSVs, you ask a question once and the model gathers what it needs across the tools. It covers the classic organic workflow — keyword discovery with volume, difficulty and CPC, which keywords a domain already ranks for, what competitors occupy a SERP — and a full local pack: Google Business Profile audits, Maps rank grids around a location, review collection and business category lookups. Project context is shared across calls, so the model keeps your business, goals and competitor set in mind between questions.

Tools the OpenSEO MCP server exposes

Typical tools an AI model can call. Exact names vary by version.

Keyword research and hydration — volume, difficulty, CPC, intent and trend data
Live Google SERP fetching and competitor comparison across keyword sets
Domain analysis — ranking keywords, organic footprint summary and backlink overview
Google Search Console performance (clicks, impressions, CTR, position) and URL inspection
Local SEO — business search, Google Business Profile audits, Maps rank grids and reviews
Project context and saved keyword lists shared across every call

Connecting to OpenSEO

Taken from the official OpenSEO documentation — see OpenSEO MCP documentation for the full reference.

URL format

https://app.openseo.so/mcp

Examples

Bearer token (headless clients)

Authorization: Bearer oseo_YOUR_KEY

Create the key in the OpenSEO app under Settings → API keys.

API key header (alternative)

x-api-key: oseo_YOUR_KEY

Equivalent to the bearer form — use whichever your client supports.

Client configuration

Claude Code

Runs the OAuth flow on first use.

claude mcp add --transport http --scope user openseo https://app.openseo.so/mcp

Cursor (mcp.json)

{
  "mcpServers": {
    "openseo": {
      "url": "https://app.openseo.so/mcp"
    }
  }
}

Codex CLI

codex mcp add openseo --url https://app.openseo.so/mcp

Example prompts to try

Copy any of these into MCP Agent Studio after connecting.

Find 20 low-difficulty keywords related to "mcp server testing" with volume above 100.
Which keywords does my domain already rank for on page 2, and what is the traffic upside?
Compare the top 10 SERP competitors for my three main keywords and tell me what they have in common.
Pull Search Console clicks and impressions for the last 28 days and flag pages losing position.
Audit my Google Business Profile and check my Maps rank grid within 5km of the storefront.

Models on MCP Playground

This is not a single-model product: you get the same MCP connection with 60+ models (Claude, GPT, Gemini, DeepSeek, open-weight, and more), you can switch mid-conversation, and you can open Compare mode to run the same prompt against multiple models at once. The card above is a suggested starting point for this server — not the only choice.

Default pick for OpenSEO

Claude Sonnet 4.5

Claude Sonnet 4.5 handles multi-step research well — chaining keyword lookups into SERP checks and summarising the result. Haiku 4.5 is enough for single metric fetches.

Open Compare mode (side-by-side)Try this server in Agent Studio

Check an AI agent can actually use the OpenSEO MCP server

Listing tools proves the server is reachable, not that a model can work with it. Evals go further: they read every tool on the server, write a test suite from its real schemas, and run it — code decides pass/fail on the responses (schema conformance, error codes, pagination, result caps) while a scoring model grades plain-English tasks driven through the tools.

Get a pass/fail report per tool with the evidence behind each verdict — and replay the same suite after every schema change. Destructive tools are excluded from the run.

Run evals

Try the OpenSEO MCP server in your browser

Open MCP Agent Studio with the connection pre-filled. Add your token, pick any of 60+ models, and start chatting — no install required.

Try OpenSEO in Agent Studio

OpenSEO MCP server — FAQ

Common questions about connecting, scoping and using it safely.

What is the OpenSEO MCP server?

It is a hosted remote MCP that OpenSEO operates at app.openseo.so/mcp, exposing its SEO research platform — keyword metrics, live SERPs, rank tracking, backlinks and Google Search Console data — as tools an AI model can call directly, instead of you exporting reports and pasting them into a chat.

How do I authenticate with the OpenSEO MCP server?

OAuth is the default: the first connection sends you through OpenSEO login, and after you authorise it the client can call tools with the project context and account scopes you approved. For headless environments where a browser flow is not practical, create a personal API key in the OpenSEO app under Settings → API keys and send it as `Authorization: Bearer oseo_YOUR_KEY`, or as an `x-api-key` header.

What can it do that a normal keyword tool cannot?

The value is chaining. A keyword tool answers one question per export; through MCP a model can discover keywords, check which ones you already rank for, pull the live SERP for the promising ones, and cross-reference Search Console performance — in a single request, keeping your project context throughout.

Does it cover local SEO as well as organic?

Yes. Alongside the organic tools it exposes local business search by coordinates, Google Business Profile audits (categories, ratings, hours, photos, claim status), Maps SERP and Business Q&A, review collection, valid business category lookups, and a Maps rank grid check around a business location.

How do I test the OpenSEO MCP server in the browser?

Open MCP Agent Studio, paste https://app.openseo.so/mcp as the server URL, add your OpenSEO API key, pick a model and start asking research questions. Every tool call is shown inline with its full JSON input and output, so you can see exactly which SEO tool the model reached for and what came back.