Connect Claude (or any AI) to your CRM via MCP

Most CRMs in 2026 are racing to add "AI features." They bolt a chat sidebar onto the UI, fine-tune some prompts, market it as transformative. The result is almost always the same: you have to learn a new chat interface inside your CRM, the AI only knows what's on the current screen, and the integration ends at the boundary of what the vendor decided to wire up.

Groundbase takes the opposite approach. Instead of adding AI to the CRM, it lets you connect YOUR AI to it. Groundbase exposes itself as a Model Context Protocol (MCP) server, which means Claude Desktop, Cursor, Windsurf, Cline, or any MCP-compatible client can talk to your real Groundbase data directly. You don't learn a new chat UI — you use whatever AI you already use, and it can now read and modify your CRM.

This post explains what that actually enables and why I built it this way.

What MCP is (briefly)

MCP — Model Context Protocol — is an open protocol introduced by Anthropic in late 2024 that standardizes how AI clients connect to external tools and data sources. Before MCP, every AI vendor had their own approach to "tool use" — ChatGPT had Custom GPT Actions, Claude had its own tool format, Cursor had MCP-like extensions. After MCP, any client that supports the protocol can connect to any server that implements it.

Think of it like USB-C for AI tools. Standardized connection, plug-and-play across compatible devices.

For a CRM specifically: an MCP server exposes a list of "tools" the AI can call (read contacts, create deals, send SMS, look up activity, etc.). The AI client connects, reads the tool list, and can call those tools when the user asks it to do CRM-related work.

What this actually enables

Concrete examples of things you can do once Claude (or your preferred AI) is connected to Groundbase via MCP:

• "Show me my deals closed this month, grouped by stage." Claude queries Groundbase, returns the data, you read it in the same Claude conversation where you're already working.
• "Draft personalized follow-up SMS for everyone tagged 'demo-requested' who hasn't been contacted in 7+ days." Claude pulls the matching contacts, drafts an SMS for each one in their voice, queues them for you to review.
• "Build me a workflow that adds a task to 'follow up Friday' whenever a deal moves to the negotiation stage." Claude calls the workflow-creation tool, sets up the trigger, confirms it's live.
• "Connect my Typeform — every submission should become a new contact, tagged 'inbound-2026-q3'." Claude calls the inbound webhook setup tool, generates the webhook URL, walks you through pasting it into Typeform.
• "Look at my dashboard summary and tell me what to focus on this week." Claude pulls dashboard data, gives you a prioritized take in plain English.
• "Find every contact with no recent activity and surface the top 5 worth re-engaging." Claude queries, ranks, presents.

Notice none of these require you to leave Claude. You're already in a Claude conversation drafting emails, writing code, thinking through problems — and now you can also ask it to do real things in your CRM in the same conversation. The CRM stops being an app you context-switch into; it becomes data your AI assistant can work with.

Which AI tools work with Groundbase

Honest breakdown of what's compatible and how:

Direct MCP support (just install + connect):

• Claude Desktop — the most polished MCP integration. Install the Groundbase MCP server in your claude_desktop_config.json, restart Claude, you're connected.
• Cursor — IDE-focused but supports MCP for general use.
• Windsurf (Codeium) — same.
• Cline — VS Code extension with MCP support.
• Continue — VS Code / JetBrains AI extension with MCP support.

Works via different protocol (OpenAPI Actions instead of MCP):

• ChatGPT (via Custom GPT) — ChatGPT doesn't speak MCP yet, but it can call Groundbase via OpenAPI Actions configured in a Custom GPT. Same end result, different setup.

Doesn't work directly but can integrate via webhooks:

• Anything else — Zapier, n8n, Make, custom code. Groundbase has webhooks both directions (inbound + outbound) so any AI tool that can call HTTPS endpoints can interact.

For most users, the answer is "use Claude Desktop." It's the cleanest experience, the protocol's reference implementation, and the integration takes about 5 minutes.

Setup

Quick overview — full setup guide lives at groundbasecrm.com/mcp:

1. Generate an MCP API key in Groundbase Settings → Integrations → MCP
2. Add the server to your Claude Desktop config:

   {
     "mcpServers": {
       "groundbase": {
         "command": "npx",
         "args": ["-y", "@groundbase/mcp-server"],
         "env": { "GROUNDBASE_API_KEY": "gbm_xxx..." }
       }
     }
   }
   

3. Restart Claude Desktop
4. Ask Claude "what Groundbase tools do you have?" — it'll list them

[SCREENSHOT — Adam to grab: Claude Desktop showing the MCP server connected (usually visible as a green dot or tool count indicator). Save as claude-mcp-connected.png in public/blog/mcp-feature/]

[SCREENSHOT — Adam to grab: a Claude conversation where you've asked it to do something Groundbase-related (e.g., "list my recent deals") and it responded with real data. Save as claude-using-groundbase.png in the same folder.]

If either is awkward to capture (e.g., shows real customer data you'd rather not publish), just skip the screenshots — the JSON config block above carries enough of the "this is what setup looks like" message on its own.

Why I built it this way

A few honest reasons:

1. I don't want to be in the AI race

Building "AI features" into Groundbase would mean picking a model provider, paying for inference, tuning prompts, maintaining quality as models change, and somehow charging for it. Every other CRM is doing this. The unit economics are bad — AI inference costs are real, and customers expect AI features included in their flat subscription, not metered separately.

By exposing MCP and letting customers bring their own AI, I avoid all of that. Inference is between you and Anthropic / OpenAI / whoever you use. Groundbase is the data layer. Cleaner separation, simpler business model, no AI feature creep.

2. The AI you already use is probably better than the one I'd build in

If you're already paying for Claude Pro or ChatGPT Plus or Cursor Pro, you're using a frontier model that's been heavily tuned for general intelligence. Anything I'd bolt into Groundbase as "our AI feature" would be a worse version of what you already have. Better to expose data well and let the good model do the thinking.

3. MCP is the right shape for a multi-tool stack

Solo operators don't use one tool — they use a stack. Groundbase for CRM, Stripe for billing, Linear or Notion for personal task management, GitHub for code, ConvertKit for marketing email. AI assistants that can reach across this stack via MCP are the actual future of how solo work gets done. Being an MCP-compatible source positions Groundbase as a citizen in that stack, not a walled garden trying to swallow adjacent tools.

(I wrote up the "won't swallow adjacent tools" philosophy here: Why Groundbase won't build social media management.)

What this is asymmetric against

Most established CRMs won't add MCP support, for two reasons:

• Their business model depends on UI lock-in. If Claude can read your contacts directly from HubSpot, you have less reason to log into HubSpot daily — which weakens HubSpot's product attachment and makes you more migratable.
• Adding MCP requires committing to an Anthropic-led protocol, which feels like ceding strategic ground for a public company that wants to control its own integration story.

Indie CRMs that are willing to make this commitment (Groundbase, a couple of others) have a real asymmetric advantage: we ARE the data layer for the AI-first workflow. Buyers building their stack around AI tools have very few options that work this way.

Try it

Start a Groundbase trial, generate an MCP key in Settings, and connect Claude Desktop in about 5 minutes. The first time you ask Claude "what's in my pipeline right now?" and get a real answer pulled from your actual deals, the value proposition lands more clearly than any feature comparison page could.

(If you want context on why the rest of Groundbase is shaped this way too, the who Groundbase is for post lays out the assumptions explicitly.)