How to Use the Ironclad MCP in Pydantic AI

Q: How do I list active agreements in progress?

Use ironcladlistworkflows to fetch the status of all active contract lifecycles. This returns a clean list of contracts currently in drafting, negotiation, or signature phases.

Q: How do I connect the Ironclad MCP Server to my Pydantic AI agent?

Install the package via pip install "pydantic-ai-slimmcp". Use the unified MCPToolset constructor pointing to your Vinkius HTTP endpoint, and pass it directly into your agent's toolsets configuration.

Q: Can I inspect webhooks configured on this Ironclad MCP Server?

Yes, the agent can call ironcladlistwebhooks to fetch all registered webhook configurations. Pydantic AI validates the returned URLs and event types, making it easy to audit your integration health.

Validate every Ironclad contract action at runtime with type-safe Pydantic AI agents that prevent legal data corruption using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ironclad MCP to Pydantic AI

Create your Vinkius account to connect Ironclad to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Ironclad with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Launch validated workflows via Pydantic AI

The `ironclad_launch_workflow` tool initiates contract generation from pre-configured legal templates. Because Pydantic AI enforces strict type safety, every input attribute—like contract value or counterparty jurisdiction—is validated against your defined Python models before hitting the API. Your agent uses `ironclad_list_templates` to verify that the target template ID exists and matches your schema. If a sales rep inputs an invalid date format, the agent fails loudly at runtime, preventing malformed contract requests from entering your legal queue.

Extract validated contract metadata

The `ironclad_get_record` tool retrieves the final, executed contract record alongside its associated legal metadata over this MCP connection. Your agent parses this response directly into strongly-typed Pydantic models to guarantee data integrity across your systems. If you need to search across your repository, `ironclad_search_records` scans historical files and returns matching agreements. The Pydantic AI framework validates the returned fields, ensuring your automated renewal pipelines never process corrupted or missing date values.

Audit active approvals with type guarantees

The `ironclad_get_approvals` tool fetches the live status of every internal and external approver assigned to a contract. Your agent parses this structured approval list to identify who is holding up the signing process. To understand the reasons behind a delay, the agent runs `ironclad_get_comments` to pull the raw discussion logs. By validating these text fields, your Pydantic AI workflow can safely extract legal feedback and route it to the correct engineering or sales channels.

Setup guide

Set up Ironclad MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "ironclad-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Ironclad tools.",
)

result = await agent.run("List recent Ironclad transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Ironclad. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Ironclad now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Ironclad MCP in Pydantic AI

Your Pydantic AI agent will raise a validation error immediately. This prevents silent failures or downstream database corruption by stopping execution the moment the API response deviates from your schema.

Use `ironclad_list_workflows` to fetch the status of all active contract lifecycles. This returns a clean list of contracts currently in drafting, negotiation, or signature phases.

Install the package via `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` constructor pointing to your Vinkius HTTP endpoint, and pass it directly into your agent's `toolsets` configuration.

Yes, the agent can call `ironclad_list_webhooks` to fetch all registered webhook configurations. Pydantic AI validates the returned URLs and event types, making it easy to audit your integration health.

Vinkius processes all API requests in an isolated, zero-trust V8 sandbox. Your sensitive legal comments, approval workflows, and contract metadata are never cached, stored, or exposed, keeping your compliance pipeline completely secure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript