PandaDoc MCP — Claude Code MCP server: what it does, how to install
Connects AI agents to the PandaDoc API and a local document store. It tracks stalled proposals, recipient engagement, and open quote value directly from your workspace.
Open on GitHubWhat PandaDoc MCP does
This server exposes PandaDoc API endpoints to your AI assistant alongside a local document storage layer. It extracts data on stalled proposals, document age, and recipient views. Open quote values compute straight from local storage.
The tool installs as two separate binaries, pandadoc-cli and pandadoc-mcp. Every MCP command shells out directly to the companion CLI. Run pandadoc-cli --version to verify the installation.
The connector must only run via stdio. Starting it with --transport http binds to every network interface without any password, leaving the endpoint exposed to arbitrary local browser requests.
What it helps with
- Query stalled proposals and unsigned documents
- Track recipient engagement and document viewing activity
- Calculate the total value of open quotes locally
- Execute PandaDoc API requests through agent tool calls
Example prompts for the agent
- Check the status of the latest proposal and see if the recipient opened it
- List stalled PandaDoc documents and calculate the total open quote value
- Run pandadoc-cli through the agent to inspect pending contract signatures
How to install PandaDoc MCP
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about PandaDoc MCP
How to install PandaDoc MCP in Claude Code?
Add the marketplace source using /plugin marketplace add Servosity/msp-skills, then install the tool by running /plugin install pandadoc@msp-skills.
What does PandaDoc MCP do?
It integrates your coding assistant with the PandaDoc API and a local document pipeline. The tool pulls proposal aging metrics, tracks recipient views, and calculates open deal amounts.
Can I run PandaDoc MCP over HTTP?
Use the stdio transport instead. The HTTP transport flag (--transport http) currently binds to all interfaces without authentication, exposing your API credentials to external web traffic.
