quip -python
Model Context Procotol(MCP) server for fetching Quip document
claude mcp add --transport stdio zxkane-quip-mcp-server-python python -m src.server --storage-path /path/to/storage \ --env QUIP_TOKEN="your_quip_api_token" \ --env QUIP_BASE_URL="https://platform.quip.com" \ --env QUIP_STORAGE_PATH="/path/to/storage"
How to use
This MCP server provides access to Quip spreadsheet data by reading documents from Quip and returning the content as CSV. It supports selecting a specific sheet by name and returning metadata about the content, such as total rows, total size, and whether the data was truncated. When handling large spreadsheets, the server saves the complete CSV to local storage and returns a truncated version (up to a defined limit) along with a resource URI that allows clients to retrieve the full content. The primary tool exposed by the server is quip_read_spreadsheet, which takes a Quip document threadId and an optional sheetName and returns a JSON payload with csv_content and metadata, including a resource_uri for full access. Resource URIs default to the quip:// protocol, with an optional file-protocol alternative that points to local CSV files when --file-protocol is used. To use from an MCP client, configure the quip server in your mcpServers section, providing the storage path and authentication token, and optionally enable the file protocol to use file:// URIs.
How to install
Prerequisites:
- Python 3.12 (as used by this project) or a compatible Python environment
- Access to the internet to install Python packages
Installation steps:
- Install Python 3.12+ if not already installed.
- Create and activate a virtual environment (optional but recommended):
- python -m venv venv
- source venv/bin/activate (Linux/macOS) or venv\Scripts\activate (Windows)
- Install the package (as described in the README, via pip):
pip install quip-mcp-server - Run the server (example using Python module invocation):
python -m src.server --storage-path /path/to/storage - If using uvx (not shown here, since this is the Python variant), you could instead run:
uvx quip-mcp-server --storage-path /path/to/storage - Set required environment variables (discussed in the next step) and ensure the storage path exists.
Optional: create a .env file in the project root with
QUIP_TOKEN=your_quip_api_token
QUIP_BASE_URL=https://platform.quip.com
QUIP_STORAGE_PATH=/path/to/storage
Additional notes
Notes and tips:
- QUIP_TOKEN is required to access the Quip API. Treat this token as a secret.
- QUIP_BASE_URL can be omitted if you are using the default Quip platform URL; you can override it if you’re pointing to a different host.
- QUIP_STORAGE_PATH controls where full CSVs are stored locally for large spreadsheets. Ensure the directory exists and is writable by the process.
- If you enable the --file-protocol option, resource URIs will use file:// and point to local CSV files; otherwise, URIs use the quip:// scheme.
- When a thread/document is not a spreadsheet, the server will return an error. If a specified sheet name is not found, an error is returned.
- This Python variant uses the src.server module; ensure your PYTHONPATH includes the project location if running from a non-installed source tree.
Related MCP Servers
Lambda
Creates a simple MCP tool server with "streaming" HTTP.
mcp-pinecone
Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG
asterisk
Asterisk Model Context Protocol (MCP) server.
mcp_autogen_sse_stdio
This repository demonstrates how to use AutoGen to integrate local and remote MCP (Model Context Protocol) servers. It showcases a local math tool (math_server.py) using Stdio and a remote Apify tool (RAG Web Browser Actor) via SSE for tasks like arithmetic and web browsing.
mcp-community
Easily run, deploy, and connect to MCP servers
Zammad
A Model Context Protocol (MCP) server for Zammad integration, enabling AI assistants to interact with tickets, users, and organizations.