PandaDoc MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect PandaDoc through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to PandaDoc "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in PandaDoc?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About PandaDoc MCP Server
Connect your PandaDoc account to any AI agent and automate your document workflows through natural conversation.
Pydantic AI validates every PandaDoc tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Documents — List, create from templates, send for signature, check status, and track viewed/completed/declined documents
- Templates — Browse all available document templates (proposals, contracts, NDAs, quotes)
- E-Signatures — Send documents for signature and monitor signing progress in real time
- Contacts — Manage recipient contacts with email, name, and company
- Team — List workspace members and their roles
The PandaDoc MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect PandaDoc to Pydantic AI via MCP
Follow these steps to integrate the PandaDoc MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 10 tools from PandaDoc with type-safe schemas
Why Use Pydantic AI with the PandaDoc MCP Server
Pydantic AI provides unique advantages when paired with PandaDoc through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your PandaDoc integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your PandaDoc connection logic from agent behavior for testable, maintainable code
PandaDoc + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the PandaDoc MCP Server delivers measurable value.
Type-safe data pipelines: query PandaDoc with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple PandaDoc tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query PandaDoc and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock PandaDoc responses and write comprehensive agent tests
PandaDoc MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect PandaDoc to Pydantic AI via MCP:
pandadoc_create_contact
Email is required. Once created, patients can be used as recipients in document creation. Returns the created contact with their PandaDoc ID. Create a new contact in PandaDoc with email, name, and company for use as a document recipient
pandadoc_create_document
templateId is required (use pandadoc_list_templates to find). Recipients array must include at least email and optionally first_name, last_name, and role (matching template roles). The document is created in "uploaded" status and transitions to "draft" within 3-5 seconds. Fields is an optional JSON object to pre-fill template tokens/variables. Create a new PandaDoc document from a template with recipients, custom fields, and pricing — ready to send for signature
pandadoc_delete_document
This is irreversible. Only documents in draft or voided status should typically be deleted. Completed/signed documents should be voided first if deletion is required for compliance reasons. Permanently delete a PandaDoc document — this action cannot be undone and removes the document from all views
pandadoc_document_status
Returns current status, last viewed/completed dates, and recipient progress. Use for tracking: "has the client signed?", "did they view it?", or status polling after sending. Check the current status of a PandaDoc document — whether it is draft, sent, viewed, completed, or declined
pandadoc_get_document
Returns document name, status, all recipients with their signing status, template reference, pricing table totals, custom field values, and metadata. Use after listing documents to drill into a specific document for complete information. Get complete details of a specific PandaDoc document by ID, including recipients, fields, tokens, pricing, and audit trail
pandadoc_list_contacts
Returns contact name, email, company, and metadata. Contacts are the people your organization sends documents to. Use when the user asks about recipients, needs to find a contact email, or wants to review the contact database. List PandaDoc contacts with names, emails, companies, and associated document history
pandadoc_list_documents
Filter by status: draft (not yet sent), sent (awaiting signatures), completed (fully signed), viewed (opened by recipient), paid, voided, or declined. Returns document name, template used, status, total value, owner email, and dates. Use when the user asks about document pipeline, pending signatures, or completed agreements. List PandaDoc documents with name, status (draft/sent/completed/viewed/paid/voided/declined), creation date, and recipient info
pandadoc_list_members
Returns member name, email, role, and status. Use when the user asks about team members, document ownership, or needs to audit workspace access. List workspace members (users) in your PandaDoc organization with their email, role, and access level
pandadoc_list_templates
Returns template name, UUID (needed for pandadoc_create_document), creation date, and folder. Templates are reusable document blueprints with pre-defined layouts, fields, and recipient roles. Use when the user asks "what templates do we have?" or needs a template ID before creating a document. List all PandaDoc templates available for document creation — proposals, contracts, agreements, NDAs, and more
pandadoc_send_document
This triggers email notifications to all recipients. Set silent=true to suppress emails (useful when embedding signing in your own app). An optional message can be included in the notification email. The document moves to "sent" status after this call. Send a PandaDoc document for signature — transitions it from draft to sent and notifies all recipients via email
Example Prompts for PandaDoc in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with PandaDoc immediately.
"Show me all proposals waiting for signature"
"Create a new NDA for Jane Doe at Global Solutions."
"Did Acme Corp sign the contract I sent yesterday?"
Troubleshooting PandaDoc MCP Server with Pydantic AI
Common issues when connecting PandaDoc to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiPandaDoc + Pydantic AI FAQ
Common questions about integrating PandaDoc MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect PandaDoc with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect PandaDoc to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.