How to Use the Inform Direct MCP in LlamaIndex

Q: Can LlamaIndex update its vector store when Inform Direct records change?

Yes. You can schedule a pipeline that calls listfilings to check for new submissions, then incrementally updates your index with the latest corporate data.

Q: Does the Inform Direct MCP Server support semantic search in LlamaIndex?

The server provides raw data tools like listdirectors, while LlamaIndex handles the vectorization and search. This separation ensures you always search against actual, unmodified corporate records.

Index live UK corporate filings directly into your LlamaIndex RAG pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inform Direct MCP to LlamaIndex

Create your Vinkius account to connect Inform Direct 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 Inform Direct with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a queryable index of your UK companies

LlamaIndex converts active Inform Direct corporate records into a searchable knowledge base. Your agent runs `list_companies` and `get_company` to pull raw entity data, which the framework indexes into a vector store. Instead of searching through static PDFs, you query your LlamaIndex vector store to find which UK entities need attention. The framework keeps your vector store updated by pulling fresh Inform Direct data directly from the API.

Semantic search with LlamaIndex

This MCP Server lets your LlamaIndex agent query historical corporate submissions. The agent executes `list_filings` to retrieve filing histories, then parses the raw text for specific financial patterns or dates. You can ask your LlamaIndex agent complex questions about shareholder changes or director appointments. The system matches your query against indexed data pulled from `list_shareholders` and `list_directors` to give you accurate answers.

Track filing deadlines with live data lookup

Avoid compliance penalties by indexing real-time deadlines directly into LlamaIndex. Your agent uses `get_filing_status` to fetch upcoming dates, blending this live data with your internal corporate calendars. LlamaIndex ensures the agent retrieves the actual API response instead of relying on outdated vector embeddings. If the connection drops, the LlamaIndex pipeline runs `check_informdirect_status` to verify the API pipeline is still active.

Setup guide

Set up Inform Direct 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 Inform Direct 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 Inform Direct tools.",
)
response = await agent.run("List recent Inform Direct 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 Inform Direct. 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 Inform Direct 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 Inform Direct MCP in LlamaIndex

Use the LlamaIndex MCP tool spec to connect to the Vinkius endpoint. The framework fetches data via `list_companies` and converts the JSON output into documents for your vector index.

Yes. You can schedule a pipeline that calls `list_filings` to check for new submissions, then incrementally updates your index with the latest corporate data.

The server provides raw data tools like `list_directors`, while LlamaIndex handles the vectorization and search. This separation ensures you always search against actual, unmodified corporate records.

Pass an allowed tools filter to the MCP client during setup. This lets you expose only read tools like `get_company` and hide write tools like `remove_company` from your agent.

Your UK statutory records, shareholder registries, and filing deadlines are protected by Vinkius's zero-trust MCP sandbox architecture. The data flows directly from the secure API to your local index without being cached or stored on external servers.

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