PiR2 Academy Sheets Reader MCP
A read-only MCP server that lets Claude Desktop read bounded data from Google Sheets using the learner's own Google account, offering tools to check connection status, connect, and fetch spreadsheet metadata or specific ranges.
README
Built for PiR2 Academy — Advanced Claude Cowork
PiR2 Academy Sheets Reader MCP
A local, read-only connector that lets Claude Desktop read bounded data from Google Sheets through a Google project and Google account owned by the learner.
What it does
The bundle exposes five stable tools:
google_auth_status— check whether Google is connected.connect_google— open Google's consent page for read-only access.get_spreadsheet_metadata— read workbook and tab metadata.read_sheet_sample— inspect a small, bounded sample.read_sheet_ranges— read explicit, bounded A1 ranges.
It cannot edit, create, or delete a spreadsheet. It does not use a PiR shared Google app, service account, remote MCP server, or OAuth broker.
Before class
- Install the current Claude Desktop release on macOS or Windows.
- Follow Set up your own Google project and download its Desktop OAuth JSON file.
- Download the
.mcpband matching.sha256files from this repository's Releases page.
Company-managed Google accounts can block third-party OAuth apps. If your administrator does not allow the connection, prepare a personal Google account and a Sheet containing non-confidential practice data.
Install in Claude Desktop
- Open the downloaded
.mcpbfile. - Confirm PiR2 Academy — Sheets Reader in Claude Desktop.
- When asked for Google Desktop OAuth credentials, choose the JSON file from your own Google project.
- Start a new Claude conversation and ask:
Check Google Sheets connection. - When Claude reports that Google is not connected, ask:
Connect Googleand complete Google's consent page in your browser.
The learner flow is the same on macOS and Windows. You do not need to use the Terminal. Keep the downloaded OAuth JSON private and do not upload it to chat, GitHub, Slack, or a shared drive.
Use it
Give Claude a Google Sheet URL and ask it to inspect the workbook or read a specific range. The Live Dashboard lab adds a separate Dashboard Skill that interprets generic Sheet data and responds to the manual command Refresh dashboard.
Read Privacy and data boundaries before using real business data. See Troubleshooting if connection or access fails.
For maintainers
Architecture and verification are documented in Architecture and Testing and evidence.
npm ci
npm run check
npm run build
npm run smoke
npm run audit:high
npm run audit:tooling
npm run scan:secrets
npm run bundle
npm run bundle:verify
Read CONTRIBUTING.md before opening a change. Report vulnerabilities through SECURITY.md.
License
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.