How to Connect PandaDoc to Claude (and What It Can't Do)
PandaDoc is one of the easy answers in this space: yes, and it’s first-party. PandaDoc builds and runs its own hosted MCP server at mcp.pandadoc.com, documented in PandaDoc’s developer guide, and as of mid-2026 PandaDoc also appears in Claude’s connector directory — so on claude.ai you can enable it and authorize with OAuth rather than juggling API keys. On Claude Code it’s one command: claude mcp add pandadoc --transport http https://mcp.pandadoc.com/v1/mcp. Adding it as a custom connector requires a paid Claude plan.
The honest caveat sits elsewhere. However you connect it, the integration lives inside conversations you start. It has no triggers, no schedules, and no awareness of anything that happens in PandaDoc while you’re not chatting — which, for a tool whose whole job is documents moving through stages, is the constraint that shapes everything below.
What Claude can actually do in your PandaDoc account
PandaDoc’s server exposes both reads and writes. In a chat, Claude can create a document from one of your templates, populate its fields and pricing table, send it to recipients, check who has viewed or signed, fire off a reminder, and search or summarize documents by status. Because the connection is OAuth’d to your account, everything runs as you — a sent proposal is genuinely sent, so review each tool call before approving it.
Some prompts a PandaDoc user would actually type:
- “Create a proposal from our Website Redesign template for this morning’s inbound lead and set the pricing table to the three-page-site tier.”
- “Which proposals have been sitting in Viewed for more than five business days? List them with the last activity date.”
- “Send a reminder on the Q3 renewal that’s still waiting on the second signer.”
For a sales or ops person, that middle prompt alone justifies the setup — PandaDoc’s dashboard shows document status, but interrogating it conversationally (“…and which of those are above $10k?”) is faster than filtering.
Where the chat boundary bites
PandaDoc runs on status changes: draft, sent, viewed, waiting for approval, completed. Its own approval workflows and expiration settings react to those states. Claude doesn’t. There is no path from a PandaDoc event to a Claude conversation — the connector can’t wake up.
Concretely: a prospect opens your proposal four times in one afternoon and doesn’t sign — the ideal moment for a nudge passes in silence. A deal moves to “Contract sent” in your CRM — nobody generates the quote until you open a chat and ask. A client countersigns Friday evening — the kickoff email and the handoff task wait for Monday. If your reason for connecting PandaDoc to an AI is “so this stuff handles itself,” a chat connector is the wrong shape, official or not.
Closing the loop with Carly
Carly is an AI executive assistant built for the event-driven half of the job. Instead of waiting in a chat, it watches for the trigger and runs the whole sequence in the cloud:
- Deal reaches the contract stage → Carly generates the document from your PandaDoc template and sends it.
- Proposal sits unsigned past your threshold → Carly drafts and sends the follow-up, and actually sends email (Gmail and Outlook), not just drafts.
- Document completes → Carly emails the countersigned copy, creates the onboarding tasks, and updates the CRM.
Setup is an interview, not an integration project: tell Carly the outcome you want in plain English and it builds the workflow with you. AI agents start at $35/month, and steps in a workflow that don’t use AI run free and unlimited. Details on the PandaDoc integration page, plus 200+ other tools under integrations.
PandaDoc through Claude vs PandaDoc through Carly
| Claude (official PandaDoc MCP) | Carly | |
|---|---|---|
| Create a document from a template | Yes, when you ask | Yes, when a trigger fires |
| Send documents and reminders | Yes (you approve each one) | Automatic, per your workflow |
| React to “viewed but not signed” | No | Yes |
| Chain PandaDoc with CRM + email steps unattended | No | Yes |
| Works while you’re offline | No | Yes (cloud) |
| Setup | OAuth connector, paid Claude plan | Plain-English interview |
| Pricing | Paid Claude plan for custom connectors | AI agents from $35/mo |
Frequently Asked Questions
Does Claude integrate with PandaDoc?
Yes — this one is official. PandaDoc operates its own MCP server at mcp.pandadoc.com/v1/mcp and is listed in Claude’s connector directory as of mid-2026. Connect via OAuth on claude.ai or add it in Claude Code; custom connectors need a paid Claude plan.
Can Claude create and send a PandaDoc document?
Yes, inside a chat. It can build a document from your templates, fill fields and pricing tables, send it, and follow its status — with you approving each action. What it can’t do is any of that unprompted.
Can Claude send a proposal automatically when a deal closes?
No. Connectors only operate inside conversations you start; there’s no listener for CRM or PandaDoc events. Trigger-driven document generation is what an agent platform like Carly is for.
Will Claude remind a signer if a document stalls?
Only if you ask it to in the moment. It has no schedule, so “remind anyone who hasn’t signed after three days” isn’t expressible. Carly runs exactly that kind of cadence on its own.
How does Carly price its PandaDoc workflows?
AI agents start at $35/month, and workflow steps that don’t use AI run free and unlimited. One agent can cover the full document lifecycle — generate, send, chase, file — across PandaDoc, email, and your CRM.
More: Claude connectors · Can Claude send emails · Claude vs Carly · Claude Cowork alternatives · Best AI tools for consultants · Claude + BoldSign · Claude + DocuSeal · Claude + Tally
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
