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.
-
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
git clone <repository-url>
cd quip-mcp-server
pip install -e .pip install -e ".[dev]"- 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
- 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- Using the console script:
quip-mcp-server- Using Python module:
python -m quip_mcp_server- Using Docker:
docker-compose upThe 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]
- 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
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
# Install development dependencies
pip install -e ".[dev]"
# Run tests with coverage
pytest
# Generate coverage reports
pytest --cov=quip_mcp_server --cov-report=htmlThe 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 -t quip-mcp-server .Apache 2.0