How to Use the Ironclad MCP in LlamaIndex

Q: How does LlamaIndex index metadata from an Ironclad contract?

The agent calls ironcladgetrecord to retrieve the structured contract metadata. This JSON payload is then converted into document nodes and stored in your vector index. You can then run semantic search queries across your entire agreement repository.

Q: Can I use the Ironclad MCP Server to feed live negotiation comments into LlamaIndex?

Yes, you can use ironcladgetcomments to extract the full discussion history of any active workflow. LlamaIndex indexes these comments to provide historical context on why specific terms were accepted. This helps prevent repeating past negotiation mistakes.

Q: How does LlamaIndex handle document templates in Ironclad?

Your pipeline uses ironcladlisttemplates to discover available contract structures and their required metadata fields. This lets your agent build query engines that know exactly what information is needed to launch a new agreement.

Q: Can I search for specific executed agreements?

You use ironcladsearchrecords or ironcladlistrecords to find files matching your criteria. The returned metadata can be indexed on the fly, allowing you to ask complex questions about dates, values, and counterparties.

Index and query your live Ironclad contract pipelines directly within LlamaIndex RAG applications.

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 LlamaIndex

Create your Vinkius account to connect Ironclad to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Search on Live Ironclad MCP Server Data

Stop guessing what is inside your executed agreements. Your LlamaIndex agent uses `ironclad_search_records` to find relevant documents and pulls their full metadata with `ironclad_get_record`. It then indexes this data so you can ask natural language questions about your legal obligations. This turns static PDFs into a dynamic, queryable knowledge base. You can quickly verify renewal dates or liability caps without opening a single file.

Index Active Workflow Discussions in LlamaIndex

Legal negotiations are messy, but the context is valuable. By using `ironclad_get_comments`, your agent can ingest internal team discussions and negotiation history directly into your vector store. This means when you ask your agent why a specific clause was changed, it can look up the exact comment thread. It grounds its answers in real team decisions rather than guessing.

Monitor and Map Active Agreement Pipelines

This MCP Server keeps a pulse on your active legal operations. The agent calls `ironclad_list_workflows` to pull active agreements and uses `ironclad_get_workflow` to inspect specific bottlenecks. You can feed this structured data straight into your index. It gives your team an instant, natural-language interface to check the health of the entire sales pipeline.

Setup guide

Set up Ironclad MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Ironclad MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Ironclad tools.",
)
response = await agent.run("List recent Ironclad data")

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 LlamaIndex

The agent calls `ironclad_get_record` to retrieve the structured contract metadata. This JSON payload is then converted into document nodes and stored in your vector index. You can then run semantic search queries across your entire agreement repository.

Yes, you can use `ironclad_get_comments` to extract the full discussion history of any active workflow. LlamaIndex indexes these comments to provide historical context on why specific terms were accepted. This helps prevent repeating past negotiation mistakes.

Your pipeline uses `ironclad_list_templates` to discover available contract structures and their required metadata fields. This lets your agent build query engines that know exactly what information is needed to launch a new agreement.

You use `ironclad_search_records` or `ironclad_list_records` to find files matching your criteria. The returned metadata can be indexed on the fly, allowing you to ask complex questions about dates, values, and counterparties.

Your active contract metadata and workflow logs are processed entirely within your secure environment. This MCP Server does not cache or store your legal records. It acts as a lightweight conduit, passing raw data straight to your index.

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