Quip MCP Server

Quip MCP Server

MCP server for reading Quip documents and spreadsheets, enabling interaction with Quip content via natural language.

Category
Visit Server

README

Quip MCP Server

A Model Context Protocol (MCP) server for reading Quip documents and spreadsheets. Works with Claude Desktop and any MCP-compatible client.

Quick Setup

Run the setup script — it will prompt for your Quip token and configure Claude Desktop automatically:

bash <(curl -fsSL https://raw.githubusercontent.com/yashjain/quip-mcp/main/setup.sh)

Or manually add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "quip": {
      "command": "npx",
      "args": [
        "-y",
        "@yashj645/quip-mcp-server",
        "--storage-path",
        "/Users/yourname/.quip-mcp/storage",
        "--file-protocol"
      ],
      "env": {
        "QUIP_TOKEN": "your_quip_api_token"
      }
    }
  }
}

Get your Quip API token from: https://your-quip-domain.quip.com/dev/token

Installation

# Run directly with npx (no install needed)
npx @yashj645/quip-mcp-server

# Or install globally
npm install -g @yashj645/quip-mcp-server

Requires Node.js v18+.

Available Tools

quip_read_document

Reads the text content of a regular Quip document (not a spreadsheet).

Parameters:

  • threadId (required): The Quip thread ID (part of the URL after your Quip domain)

Example:

{ "threadId": "AbCdEfGhIjKl" }

Response:

{
  "thread_id": "AbCdEfGhIjKl",
  "title": "My Document",
  "type": "document",
  "text_content": "Full plain text content of the document...",
  "word_count": 342
}

quip_read_spreadsheet

Reads a Quip spreadsheet and returns its content as CSV.

Parameters:

  • threadId (required): The Quip thread ID
  • sheetName (optional): Name of the sheet to read. Defaults to the first sheet.

Example:

{ "threadId": "AbCdEfGhIjKl", "sheetName": "Sheet1" }

Response:

{
  "csv_content": "header1,header2\nvalue1,value2\n...",
  "metadata": {
    "total_rows": 1000,
    "total_size": 52840,
    "is_truncated": true,
    "resource_uri": "file:///Users/yourname/.quip-mcp/storage/AbCdEfGhIjKl-Sheet1.csv"
  }
}

Content is truncated at 10KB in the response. The full CSV is saved locally and accessible via resource_uri.


Finding the Thread ID: It's the segment in the Quip URL right after your domain.
Example: https://yourcompany.quip.com/S6eaArZiT0xy/Doc-Title → thread ID is S6eaArZiT0xy

Usage with Claude

Once set up, ask Claude:

  • "Read the Quip document with thread ID S6eaArZiT0xy"
  • "Read the Quip spreadsheet with thread ID AbCdEfGhIjKl"
  • "Read the sheet named 'Q1 Data' from the Quip spreadsheet AbCdEfGhIjKl"

Command Line Arguments

Argument Description Default
--storage-path <path> Where to store CSV files locally ~/.quip-mcp-server/storage
--file-protocol Use file:// URIs for resource access off
--port <port> Run as HTTP server on this port stdio mode
--mock Use mock data (no Quip token needed) off
--debug Enable debug logging off
--storage-type <type> local or s3 local
--s3-bucket <name> S3 bucket (when using S3 storage) —
--s3-region <region> S3 region —

Environment Variables

QUIP_TOKEN=your_token           # Required (unless --mock)
QUIP_BASE_URL=https://platform.quip.com  # Optional
QUIP_STORAGE_PATH=/path/to/storage       # Optional
STORAGE_TYPE=local              # 'local' or 's3'

HTTP Mode (for team sharing)

Run as a shared HTTP server so others on your team can connect without installing anything locally:

QUIP_TOKEN=your_token npx @yashj645/quip-mcp-server --port 3000

Others then configure:

{
  "mcpServers": {
    "quip": {
      "url": "http://your-server:3000/mcp"
    }
  }
}

Development

git clone https://github.com/yashj645/quip-mcp-server.git
cd quip-mcp-server
npm install
npm run build
npm test

Mock mode (no Quip token needed):

node dist/index.js --mock --storage-path ./storage

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured