Python · Agent framework

Use OpenRegistry from LangChain

Use OpenRegistry from LangChain / LangGraph — live company-registry data as LangChain tools.

LangChain's official adapter converts any MCP server into native LangChain tools. OpenRegistry appears as 27 callable tools plus 10 prompt workflows. Works with any LangGraph agent, any model provider.

Install

pip install langchain-mcp-adapters langchain-anthropic langgraph

Minimum working example

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic

client = MultiServerMCPClient({
    "openregistry": {
        "url": "https://openregistry.sophymarine.com/mcp",
        "transport": "streamable_http",
    }
})
tools = await client.get_tools()

model = ChatAnthropic(model="claude-3-5-sonnet-latest")
agent = create_react_agent(model, tools)

result = await agent.ainvoke({
    "messages": "Find REVOLUT LTD in the UK, list its directors, and summarise the latest accounts."
})
print(result["messages"][-1].content)

What you get

27 tools — search, profile, officers, PSC/UBO, shareholders, filings, XBRL accounts, charges, documents. See the full catalogue.
10 named workflow prompts — KYC dossier, UBO chain-walker, shell-company detector, phoenix-fraud radar. See all 10.
27 national registries — UK Companies House, Norway Brreg, Germany Handelsregister, France RNE, Spain BORME, Korea OpenDART, Canada CBCA, and more. See the map.
Live + source-linked — every field traces back to the government register. No aggregator markup.
Free tier: 20 req/min per IP, no signup, no API key.

Framework docs

Official MCP integration docs for LangChain:

langchain-ai/langchain-mcp-adapters ›

Use from a different framework?

OpenRegistry is a Model Context Protocol server. Any MCP client can connect — these are just the most popular agent frameworks.