Connect Claude to growResonance
Connect your own Claude to your workspace and let it put your recommendations into practice.
What you need
- Access to the workspace you connect. For the “Read and report back” permission, the Owner or Admin role.
- An active growResonance subscription (a trial is enough).
- For option A: a Claude account on claude.ai (Free, Pro, Max, Team or Enterprise).
- For option B: Claude Code or Claude Desktop in a version that supports MCP servers over HTTP.
Setup
MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external data sources.
With the growResonance connection, your own Claude reads the data of your workspace: visibility, prompts, competitors, sources and sentiment, plus the recommendations including ready-made building blocks such as FAQ JSON-LD, schema markup, meta tags and draft texts. It can put them into practice where your website lives: in your repository, your CMS or your editor.
growResonance itself does not write anything on your website. Access is read-only; the only exceptions are checking off a completed recommendation and reporting back an article URL, so your dashboard stays in sync.
Two options: which one fits you?
| Option A: sign-in | Option B: connection key | |
|---|---|---|
| Where | claude.ai in the browser and in the Claude app | Claude Code, Claude Desktop |
| What you enter | only the server address | server address and a key |
| Sign-in | once in the browser, with a confirmation page | none |
| Revoke | in growResonance under “Connected apps” | in growResonance via “Revoke” |
Option A: connect Claude.ai by signing in
- Copy the server address
In growResonance, open Settings → Integrations and click “Connect” in the “Claude” row. On the “Connect AI” page, Claude is already selected; click “Connect with Claude”. This copies the server address to your clipboard and opens Claude in a new tab. - Add the connector in Claude
In Claude, go to Customize → Connectors, click the plus icon and then “Add custom connector”. Paste the copied server address and confirm with “Add”. There is no field for a key here, and none is needed. - Confirm access
Claude redirects you to growResonance. Sign in if you have not already, choose the workspace Claude may see, and confirm. You are then back in Claude and the connector is connected. - Turn it on in the chat and test it
A connector works per conversation. In the chat, click the plus icon at the bottom left, then “Connectors”, and turn on growResonance. Then ask for your open recommendations. If a list comes back, the connection works.
Option B: Claude Code or Claude Desktop with a connection key
- Check your permission
Only owners and admins can create the connection key. You can see your role under Settings → Team. The key belongs to the workspace, not to you as a person, so it keeps working after a role change. - Create a connection key
Open Settings → Integrations → “Claude” row (“Connect”, or “Manage connection” in the “…” menu), and on the “Connect AI” page click “Create connection key” in the bottom section “Alternative: static connection key”. The key is shown in full exactly once. Copy it right away and keep it like a password. After that you only see the prefix, for example “grmcp_ab12cd…”. - Add the key to Claude
Enter the address and key in your MCP configuration (snippet below). In Claude Code this is the .mcp.json file in your project directory, in Claude Desktop the app’s MCP server configuration. Then restart Claude. - Test the connection
Ask Claude for your open recommendations. If a list comes back, the connection works. In the settings you can also see when the key was last used.
Example configuration (.mcp.json)
{
"mcpServers": {
"growresonance": {
"type": "http",
"url": "https://www.growresonance.ai/api/mcp",
"headers": {
"Authorization": "Bearer grmcp_YOUR_CONNECTION_KEY"
}
}
}
}What you can do with the connection
With the connection, Claude reads your growResonance analysis. Instead of copying findings out of the dashboard, you ask for them in the chat and have them implemented where your website lives.
- Ask about your own visibility per model, period and location, with the same numbers as in growResonance.
- Compare competitors and cited sources, and see the sentences in which a source appears in the answers.
- Get open recommendations sorted by priority and explained, including why a recommendation comes first.
- Use the ready-made artifact of a recommendation: FAQ JSON-LD, schema markup, meta tags or a draft text, added in the right place.
- Work through the issues from the last Technical Audit, each with affected page, severity and specific fix instructions, filterable by critical, warning and notice.
- Get the full text of a GEO article as Markdown or as finished HTML and move it into your CMS, repository or editor.
- Report back what is done: check off a recommendation or enter the live URL of a published article so the dashboard stays in sync.
What the connection accesses
Access is limited to 17 clearly defined tools. Claude does not get open access to your account but can query and report back exactly the following:
| Tool | Which data | Direction |
|---|---|---|
| Workspace overview | Brand and domain, measured models and measurement frequency, markets, locations, number of competitors, last completed run, active prompts and plan limit, Search Console status. | reads |
| Get visibility | Visibility, share of voice, average position and sentiment of your own brand per model, period and day, with the change from the previous period. | reads |
| List prompts | Your prompts with ID (P-n), status, overall visibility and visibility per model in the last run, trend, mentions and average position. | reads |
| Get a prompt with answers | One prompt with its history and, per model, the answer from the last run: mentioned yes or no, position, brands named, cited sources and answer text. | reads |
| Compare competitors | Ranking of all brands with visibility, share of voice, average position, sentiment, citation rate and visibility per model. | reads |
| List sources | Most cited domains and pages with number of citations, prompts, models, source type and the share of answers that name your brand. | reads |
| Source details | One domain with citation rate, pages, citations per model and day, and the sentence from the answer in which the source appears. | reads |
| Get sentiment | Sentiment toward the brand (0–100), positive, neutral and negative shares, praise and criticism per attribute with verbatim sentences, comparison with competitors. | reads |
| List researched prompts | Prompts from Prompt Research with area, intent, demand, Google and AI search volume, evidence and status. | reads |
| Get Search Console data | Clicks, impressions, CTR and average position from the connected Search Console, plus the strongest queries and pages. Only the numbers, never access to Google. | reads |
| List recommendations | Your open and in-progress tasks from the AEO Strategy: ID (for example A-48), key, type, category, status, priority, title, rationale and the kind of attached artifact. | reads |
| Get a recommendation | A single task with steps, acceptance criteria and affected page, plus, if available, the ready-made building block to use: FAQ JSON-LD, schema markup, meta tags or a draft text. | reads |
| List articles | Your GEO articles: title, slug, status, GEO score, word count, archetype and the live URL, if published. | reads |
| Get article content | The full text of an article as Markdown and as complete HTML, plus the meta description. | reads |
| List audit issues | The findings of the last completed audit run (page speed, AI optimization and SEO), each with severity, affected page URL and fix instructions. | reads |
| Mark a recommendation as done | Sets a task to done, like checking it off in the AEO Strategy. Safe to repeat; dismissed tasks stay dismissed. | writes |
| Report an article as published | Enters the live URL of an article that is already published and sets its status to published. | writes |
What the connection does NOT access
- No credentials: not your password, not the logins of connected accounts (for example Google), not stored API keys.
- No billing data: no invoices, no payment methods, no access to Stripe. From your plan, only the number of allowed prompts.
- No account or team data: no members, no email addresses, no roles, no invitations.
- No data from other workspaces, even if you own several.
- No dismissed recommendations: suggestions you have hidden stay hidden and cannot be brought back through the connection.
- Nothing created, nothing deleted: the connection cannot create or remove prompts, tasks, articles or audit runs.
Example prompts to try
- “How has our visibility developed over the last 30 days?”
- “Show me my open growResonance recommendations.”
- “Take the most important open recommendation and implement it in this repository.”
- “Get the FAQ schema from the recommendation and add it to the right page.”
- “Get the content of my latest growResonance article as Markdown.”
- “Show me the critical issues from my last Technical Audit and fix them in this repository.”
- “The recommendation is implemented. Mark it as done.”
Troubleshooting and FAQ
The connector is connected, but Claude doesn’t use it.
A connector has to be turned on per conversation: in the chat, click the plus icon at the bottom left, then “Connectors”, then turn on growResonance. In an old conversation that started before you connected, it may not appear. Start a new one.
Claude can’t find the server (option B).
Check three things: Did you copy the full key, including the prefix “grmcp_”? Is the word “Bearer” followed by a space in front of the key? Did you restart Claude after changing the configuration file? After that, a look at the settings helps: if the card still shows “Never used”, no request reached us.
How do I revoke access?
Option A: under Settings → Integrations, open the “…” menu of the “Claude” row, choose “Manage connection”, then click “Disconnect” in the “Connected apps” list. Option B: click “Revoke” in the “Static connection key” section; the key stops working immediately. “Regenerate” gives you a fresh key and automatically invalidates the old one. There is always exactly one valid key per workspace.
I didn’t copy the key. How do I get it back?
You can’t: we store the key only as a one-way checksum, not in plain text. Create a new key in the settings (the old one automatically stops working) and enter it in your configuration again.
Does this require a specific plan?
The connection is included in all active plans, including the trial. It is read access to data you already see in the dashboard. Anyone with access to the workspace can connect: members with the “Read only” permission, owners and admins also with “Read and report back”. If your subscription expires, access pauses until there is an active plan again; the connection itself stays in place and works again afterwards.
Is there a request limit?
Yes, 60 requests per minute per workspace. Setting up a connection takes two to three requests, each tool call one; even 20 tool calls in a minute use only a third of the limit. The limit protects against endless loops, not against your work. If it is reached, the server responds with “Too many requests”. Waiting one minute is enough.
Does growResonance see what the AI does with the data?
No. The AI runs in your own environment and works there with your permissions. growResonance only logs which tool was queried when and for which workspace, for traceability and abuse protection. Your conversations, your code and your files are not visible to us.