Ironclad 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 Ironclad 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 Ironclad "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in Ironclad?"
)
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 Ironclad MCP Server
Connect your Ironclad account to any AI agent and manage your entire contract lifecycle through natural conversation.
Pydantic AI validates every Ironclad 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
- Workflows — List active contract workflows, check current step, and track progress through review, approval, and signature
- Launch Contracts — Start new NDAs, MSAs, SOWs, or any contract type from pre-built templates with counterparty details
- Records — Search and browse the executed contract repository with key dates, values, and renewal terms
- Approvals — Check who approved, who is pending, and unblock stuck contracts
- Templates — Browse available contract types ready to launch
- Comments — Review internal discussion threads and negotiation notes on any contract
The Ironclad 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 Ironclad to Pydantic AI via MCP
Follow these steps to integrate the Ironclad 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 Ironclad with type-safe schemas
Why Use Pydantic AI with the Ironclad MCP Server
Pydantic AI provides unique advantages when paired with Ironclad 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 Ironclad integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Ironclad connection logic from agent behavior for testable, maintainable code
Ironclad + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Ironclad MCP Server delivers measurable value.
Type-safe data pipelines: query Ironclad with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Ironclad tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Ironclad and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Ironclad responses and write comprehensive agent tests
Ironclad MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect Ironclad to Pydantic AI via MCP:
ironclad_get_approvals
Returns each approver with their status (approved/pending/rejected), approval date, and any comments. Essential for tracking where a contract is stuck in the approval process. Use when the user asks "who still needs to approve this contract?" or "why is this contract delayed?" Get the approval status of a specific Ironclad contract workflow — who approved, who is pending, and who rejected
ironclad_get_comments
Returns each comment with author, timestamp, and message. Comments capture internal review discussions, legal feedback, and negotiation notes. Use to review the discussion history of a contract or understand decision context. Get all comments and discussion on an Ironclad contract workflow — internal team communication and negotiation notes
ironclad_get_record
Use for contract lookups, renewal planning, or compliance reviews. Get complete details of an executed Ironclad contract record — all metadata, dates, obligations, and linked documents
ironclad_get_workflow
), current workflow step, assigned reviewers and approvers, counterparty name, related document links, and complete timeline of actions. Use to drill into a specific contract for status updates or details. Get full details of a specific Ironclad contract workflow — current step, all attributes, counterparty info, and timeline
ironclad_launch_workflow
Attributes is a JSON object containing the contract-specific fields defined in the template (e.g., counterparty name, contract value, effective date, jurisdiction). The workflow immediately enters the first step (typically internal review or drafting). Launch a new Ironclad contract workflow from a template — start the process for an NDA, MSA, SOW, or any configured contract type
ironclad_list_records
Returns contract name, counterparty, contract type, key dates (effective, expiration, renewal), total value, and status. Records are the final, executed versions of contracts. Use when the user asks about existing agreements, upcoming renewals, or the contract repository. List executed contract records in Ironclad — fully signed agreements stored in the contract repository with key metadata
ironclad_list_templates
Each template defines: the contract type (NDA, MSA, SOW, amendments, etc.), required attributes/fields, approval chain, and signature requirements. Template IDs are needed to launch new workflows via ironclad_launch_workflow. Use when the user asks "what contract types can we create?" or needs a template ID. List available Ironclad workflow templates — NDA, MSA, SOW, and other pre-configured contract types ready to launch
ironclad_list_webhooks
Webhooks are used to notify external systems when events occur in Ironclad (e.g., workflow launched, contract signed). Returns webhook ID, name, target URL, and events. Use when auditing integrations or checking connectivity. List all configured webhooks in Ironclad — monitor external notifications for workflow events
ironclad_list_workflows
Each workflow represents a contract moving through its lifecycle: drafting → internal review → approval → counterparty negotiation → signature → execution. Returns workflow name, current step/status, creator, counterparty, template used, and dates. Use when the user asks about contracts in progress, pending approvals, or the contract pipeline. List Ironclad contract workflows in progress — NDAs, MSAs, SOWs, and other agreements moving through approval and signature stages
ironclad_search_records
Matches contract names, counterparty names, descriptions, and attribute values. Use when the user asks "find our contract with Acme", "show all NDAs", or needs to locate a specific agreement by keyword. Search Ironclad contract records by keyword — find specific agreements, counterparties, or contract types across the repository
Example Prompts for Ironclad in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Ironclad immediately.
"Show me all contracts pending approval this week"
"Launch an NDA for Acme Corp."
"Search for all active MSAs renewing next month."
Troubleshooting Ironclad MCP Server with Pydantic AI
Common issues when connecting Ironclad to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiIronclad + Pydantic AI FAQ
Common questions about integrating Ironclad 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 Ironclad 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 Ironclad to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.