quip-mcp
Enables AI assistants to read, search, create, and edit Quip documents through the MCP protocol.
README
Quip MCP Server
An MCP (Model Context Protocol) server for interacting with Quip documents. This server enables AI assistants like Amazon Q to read, search, and modify Quip documents through a standardized interface.
Features
-
Document Operations
- Read document content
- Search across documents
- Create new documents
- Append content to documents
- Prepend content to documents
- Replace document content
-
Integration Features
- MCP protocol support
- Configurable logging
- Environment-based configuration
- Docker support
Installation
From Source
git clone <repository-url>
cd quip-mcp-server
pip install -e .
Development Installation
pip install -e ".[dev]"
Requirements
- Python 3.8 or higher
- Required packages (installed automatically):
- strands-agents>=1.3.0
- mcp>=1.12.3
- python-dotenv>=1.0.0
- requests>=2.25.0
- uvicorn>=0.23.1
- httpx>=0.24.0
- starlette>=0.27.0
Configuration
- Copy the example environment file:
cp .env.example .env
- Configure your environment variables in
.env:
# Quip API credentials
QUIP_ACCESS_TOKEN=your_quip_access_token_here
QUIP_BASE_URL=https://platform.quip-amazon.com
# MCP server configuration
MCP_SERVER_PORT=8080
MCP_SERVER_HOST=localhost
# Logging configuration
LOG_LEVEL=INFO # Options: DEBUG, INFO, WARNING, ERROR, CRITICAL
Usage
Starting the Server
- Using the console script:
quip-mcp-server
- Using Python module:
python -m quip_mcp_server
- Using Docker:
docker-compose up
Available Tools
The server provides the following MCP tools:
| Tool Name | Description | Parameters | Example Usage |
|---|---|---|---|
read_document |
Read a document's content | thread_id |
"Show me the content of the Quip document with thread ID 'ABC123'" |
search_documents |
Search for documents | query, count (optional) |
"Find all Quip documents containing 'project planning'" or "Show me the 5 most recent documents about AWS" |
create_document |
Create a new document | title, content |
"Create a new Quip document titled 'Meeting Notes' with content 'Agenda items for today:'" |
append_content |
Add content to end | thread_id, content |
"Add 'Action items completed' to the end of document ABC123" |
prepend_content |
Add content to beginning | thread_id, content |
"Insert 'DRAFT:' at the start of document ABC123" |
replace_content |
Replace document content | thread_id, content |
"Replace the content of document ABC123 with 'Updated project timeline'" |
get_folder |
Get details of a specific folder | folder_id |
"Show me the contents of the Quip folder with ID 'XYZ789'" |
get_folders |
Get a list of folders | ids (optional) |
"List all my Quip folders" or "Show me details of folders ABC123, XYZ789" |
Example conversations with Amazon Q:
User: "Can you read my latest meeting notes from Quip?"
Q: Let me search for and read your meeting notes document.
[Uses search_documents followed by read_document]
User: "Create a new Quip document for today's sprint planning"
Q: I'll create a new document with a standard sprint planning template.
[Uses create_document with appropriate title and content]
User: "Add today's action items to my project notes"
Q: I'll append the action items to your project document.
[Uses append_content to add new items]
Using with Amazon Q
- Add the MCP server to Q CLI:
q mcp add quip http://localhost:8080
- Use in conversations with Q:
@q Use quip___read_document to read the document with ID "ABC123"
@q Search Quip documents for "meeting notes" using quip___search_documents
Development
Project Structure
quip_mcp_server/
├── __init__.py # Package initialization
├── __main__.py # Entry point
├── logging_config.py # Centralized logging configuration
├── quip.py # Core Quip API client
├── quip_edit.py # Document editing functionality
└── strands_agent.py # MCP agent implementation
tests/
├── __init__.py # Test package initialization
├── conftest.py # Test fixtures and configuration
├── test_logging_config.py # Tests for logging configuration
├── test_main.py # Tests for main module
├── test_quip.py # Tests for Quip client
├── test_quip_edit.py # Tests for document editing
└── test_strands_agent.py # Tests for MCP agent
Running Tests
# Install development dependencies
pip install -e ".[dev]"
# Run tests with coverage
pytest
# Generate coverage reports
pytest --cov=quip_mcp_server --cov-report=html
The current test suite provides approximately 50% code coverage, focusing on the core functionality. The main module tests are currently skipped as they require more complex mocking.
Docker Build
docker build -t quip-mcp-server .
License
Apache 2.0
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.