Claude + Notion MCP Demo
Runs an offline MCP server over a synthetic two-client workspace, enabling safe page searches and table edits while refusing ambiguous requests.
README
Claude + Notion MCP Demo
A small, offline MCP server over a synthetic two-client workspace (Acme / Beta). It shows the part of the job that is easy to get wrong: find the right page, patch one table cell, or refuse if the match is ambiguous.
This is not your live Notion workspace. There is no Anthropic API key and no Notion token in this repo. Connecting the official Notion connector still happens in your Claude Desktop app, on a screen share, with you signed in.
What it demonstrates
- A mixed workspace: text briefs plus invoice tables for two clients
search_pages— “Acme invoices” does not return Betaapply_client_edit— updatesINV-104on Acme only; a vague query like “invoices” is refused so the wrong client is not patched- Optional: point Claude Desktop at
src.serverusingclaude_desktop_config.example.json
Run it
py -3 -m pip install -r requirements.txt
py -3 -m pytest tests -q
py -3 -m src.run
src.run searches Acme invoices, sets INV-104 amount to 1500.00, leaves Beta unchanged, and shows the refused ambiguous edit.
Scope of this dummy
- Fixture JSON pages, not production Notion
- Local stdio MCP tools only
- Does not replace the Zoom/Meet walkthrough of Claude Desktop → Settings → Connectors → Notion OAuth
What the $30 call covers
The $30 milestone is: connect the official Notion MCP connector on screen share and confirm Claude can read one of your pages. You keep passwords. An NDA can be signed before the call.
It is not a promise that every client page in a mixed workspace will update correctly in 30 minutes. Reliable find-and-edit across several businesses is a follow-on milestone after we look at 2–3 example pages.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.