PandaDoc MCP: The Official Hosted Server, Explained
Yes — PandaDoc has an official MCP server. The remote server at mcp.pandadoc.com lets any MCP-compatible AI tool read and write your PandaDoc workspace — documents, templates, signing status, and more. PandaDoc announced it as a native, AI-first release in September 2025, so if you’re searching “PandaDoc MCP,” the connection you want is real and it’s hosted for you.
The thing worth knowing before you set it up: an MCP server hands your documents to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches PandaDoc for you, nothing fires when a proposal gets signed, and nothing runs while the chat is closed. Here’s exactly what the PandaDoc MCP does, how to turn it on, where it stops — and what to use when you want PandaDoc work that runs on its own.
Looking beyond PandaDoc? MCP servers by category covers the rest.
What the PandaDoc MCP server does
Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Cursor, and others — talk to an outside app through a shared interface. PandaDoc’s is a remote, hosted server exposing its core document and template operations as tools any MCP-compatible client can discover and call. It’s read and write, not read-only. With it connected, an AI client can:
- Look up and search documents — “show me every proposal sent to Acme this quarter that’s still unsigned,” answered from your live workspace instead of a guess.
- Create documents from templates — pick a template, merge the variables, and draft an agreement without opening PandaDoc.
- Send and track — set signing order, send for signature, check status, and pull the audit trail.
- Handle the housekeeping — list templates and their fields, mark a document paid or declined, remind unsigned signers, or expire stale drafts.
It’s genuinely useful for ad-hoc work: ask about a deal’s document status, spin up a proposal from a template, or send a reminder — all from a chat, grounded in real PandaDoc data.
How to set up the PandaDoc MCP server
The remote server is the quick path — no code, no hosting:
- In your AI client’s connector settings, add a remote MCP server pointing at
https://mcp.pandadoc.com/v1/mcp. - Authorize it against your PandaDoc account through the OAuth prompt — click Allow access to consent, and the client gets the same access your logged-in user has.
- Confirm the tools appear in the client, then start a chat and ask it to read or search a document first before trusting it with sends or edits.
PandaDoc’s developer docs cover the per-client setup — Claude, Cursor, ChatGPT, and custom agents all connect to the same hosted endpoint.
Where the PandaDoc MCP stops
None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:
- It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch PandaDoc; it waits for you to ask.
- No triggers. A document getting signed, a proposal going unopened for a week, a payment marked complete — none of these can start anything through MCP. There’s no “when this happens in PandaDoc, do that.”
- It’s one app at a time. The PandaDoc MCP knows PandaDoc. Getting a signed contract into your CRM, a Slack channel, and an invoicing tool means wiring up (and authing) a separate MCP server for each, then hoping your client can juggle them in one turn.
- You own the plumbing and the scopes. The OAuth grant carries read/write access to every document in the workspace, and managing what that access can touch is on you.
So the PandaDoc MCP is a great way to ask about your documents and make one-off edits or sends. It is not a way to make PandaDoc run — to have work happen on a schedule or in reaction to an event, across the other tools a signed agreement touches.
Running PandaDoc work that doesn’t need a chat open
That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to PandaDoc natively — no MCP server to host, no OAuth plumbing to maintain — and to the ~260 other apps it supports, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so PandaDoc work happens whether or not anyone has a chat window open.
A few things that MCP can’t do but a Carly workflow can:
- When a document is signed in PandaDoc → create the customer in Stripe, post to the
#closed-wonSlack channel, and add a row to your revenue sheet — automatically, the moment it happens. - Every morning → find proposals sent more than 5 days ago with no signature and send the list to the deal owner with a suggested nudge.
- When a new deal reaches a stage in HubSpot → generate the PandaDoc proposal from the right template, merge the deal values, and route it for signature.
The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the PandaDoc connection and everything downstream.
If you just want to interrogate or send documents from a chat, PandaDoc’s official MCP server is the right tool and it’s included with your account. If you want PandaDoc to actually do things — on a trigger, on a schedule, across every app an agreement flows through — that’s the job MCP wasn’t built for, and it’s the one Carly was.
FAQ
Does PandaDoc have an official MCP server?
Yes. PandaDoc runs a remote, hosted MCP server at https://mcp.pandadoc.com/v1/mcp, announced as a native AI-first release in September 2025. It gives MCP-compatible AI tools read/write access to your documents, templates, and signing workflows.
Is the PandaDoc MCP server free? Connecting it is included — you authorize an AI client against your existing PandaDoc account through OAuth, so there’s no separate MCP fee. You still need a PandaDoc plan for the documents your workspace holds.
Can the PandaDoc MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven PandaDoc work across apps — like acting the moment a document is signed — you need a workflow tool like Carly rather than an MCP server.
Can I connect PandaDoc to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to PandaDoc for you and lets you build the automation in plain language — describe what you want to happen and it wires up the documents and the other apps involved, with no server to host and no code to write.
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."
