🏢 Bolagsinfo × Notion MCP Server

DEV.to Notion MCP Challenge 2026

An MCP (Model Context Protocol) server that connects Bolagsinfo.com — a Nordic B2B lead intelligence platform with 2.4 million+ companies — to Notion. This lets AI agents like Claude, Windsurf, and Cursor search Nordic company leads, push them to Notion databases, enrich them with AI-powered Buy Signals (Köpsignaler), and manage a complete sales pipeline — all through natural language conversation. No clicking, no copy-pasting, no tab-switching. Just tell your AI assistant what you need and watch your Notion CRM fill up with qualified leads.

⚡ 5-Minute Setup

1. Clone & install

git clone https://github.com/cedendahlkim/bolagsinfo-notion-mcp.git
cd bolagsinfo-notion-mcp
pip install -r requirements.txt

2. Get your Notion API key

1. Go to notion.so/my-integrations

2. Click "New integration"

3. Name it Bolagsinfo MCP, select your workspace

4. Copy the Internal Integration Secret (starts with ntn_)

5. Important: Share your target Notion page with this integration (click ••• → "Connect to" → "Bolagsinfo MCP")

3. Configure environment

cp .env.example .env
# Edit .env and add your NOTION_API_KEY

4. Run the server

# Stdio transport (for Claude Desktop / Windsurf / Cursor)
python server.py

# SSE transport (for Docker / remote)
python server.py --sse

# Or with Docker
docker-compose up

5. Connect to your AI assistant

Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "bolagsinfo": {
      "command": "python",
      "args": ["server.py"],
      "cwd": "/path/to/bolagsinfo-notion-mcp",
      "env": {
        "NOTION_API_KEY": "ntn_your_key_here"
      }
    }
  }
}

Windsurf — add to MCP server settings:

{
  "mcpServers": {
    "bolagsinfo": {
      "command": "python",
      "args": ["/path/to/bolagsinfo-notion-mcp/server.py"],
      "env": {
        "NOTION_API_KEY": "ntn_your_key_here"
      }
    }
  }
}

Related MCP server: Personupplysning MCP Server

🛠️ MCP Tools

💬 Example Conversation

Here's a real workflow — from search to pipeline analytics — in one conversation:

Step 1: Search for leads

You: Hitta 10 e-handelsföretag i Stockholm med hög köpsignal

AI: Found 10 e-commerce companies in Stockholm:

Company	Buy Signal	Email	Industry
Nordic E-com AB	87	info@nordicecom.se	E-handel
ShopFlow Sweden	82	hello@shopflow.se	Digital handel
...	...	...	...

Step 2: Create a Notion database

You: Skapa en Notion-databas för dessa leads på min sida

AI: ✅ Created "Bolagsinfo Leads" database. Database ID: abc123...

Step 3: Push leads to Notion

You: Pusha alla 10 företagen till databasen

AI: ✅ Synced 10 leads to Notion:

• Created: 10

• Updated: 0

• Errors: 0

Step 4: Check pipeline

You: Visa pipeline-sammanfattning

AI: 📊 Pipeline Summary:

• Total leads: 10

• Status: New (10)

• Avg Buy Signal Score: 78.5

• Email coverage: 80%

• Top municipality: Stockholm (10)

Step 5: Enrich a specific lead

You: Berika det första företaget med färsk data

AI: ✅ Enriched "Nordic E-com AB":

• Buy Signal Score: 87

• Digital Maturity: 72

• CMS: WooCommerce

• Has Chatbot: No ← opportunity!

📸 Notion Database Result

After pushing leads, your Notion database looks like this:

Each lead includes company info, Buy Signal Score, AI Category, Digital Maturity, tech stack analysis, and pipeline status — all synced from Bolagsinfo.com.

🏗️ Architecture

┌──────────────┐     MCP (stdio/SSE)     ┌──────────────────────┐
│  AI Agent    │ ◄──────────────────────► │  Bolagsinfo MCP      │
│  (Claude,    │                          │  Server (FastMCP)     │
│   Windsurf,  │                          │                      │
│   Cursor)    │                          │  ┌────────────────┐  │
└──────────────┘                          │  │ 5 MCP Tools    │  │
                                          │  └───────┬────────┘  │
                                          │          │           │
                                          │  ┌───────▼────────┐  │
                                          │  │ Services       │  │
                                          │  │ • Bolagsinfo   │──────► bolagsinfo.com API
                                          │  │ • Notion       │──────► Notion API
                                          │  └────────────────┘  │
                                          └──────────────────────┘

🔑 Key Features

• 2.4M+ companies — Search the largest Nordic B2B database

• AI Buy Signals — Every company scored 0-100 on purchase likelihood

• Smart upsert — No duplicates. Updates existing leads, creates new ones.

• Rate limit aware — Respects Notion's 3 req/s limit with async semaphore

• Full CRM schema — 18 fields including tech stack, digital maturity, chatbot detection

• Pipeline analytics — Status breakdown, score averages, email coverage in seconds

• Zero config — Just add your Notion API key and go

📊 What is a Buy Signal Score?

Bolagsinfo.com analyzes every company across multiple dimensions:

• Digital presence — Website quality, SSL, mobile optimization

• Tech stack gaps — Missing chatbot, outdated CMS, no analytics

• Growth signals — Employee growth, new registrations, industry trends

• Engagement readiness — Has email, social presence, decision-maker accessibility

A score of 70+ means the company is a hot lead — they have clear digital gaps that your services can fill.

🇸🇪 Built by Gracestack AB

Gracestack AB builds AI-powered tools for B2B sales in the Nordics. Bolagsinfo.com is our flagship product — used by sales teams across Sweden and Norway to find, qualify, and close deals faster.

Kim Cedendahl & Sofia Cedendahl — Co-founders & Developers (50/50 owners of Gracestack AB)

• 🌐 bolagsinfo.com

• 🐦 @gracestack

• 💼 LinkedIn

📄 License

MIT — use it, fork it, build on it.