How to Use the CB Insights MCP in LangChain

Q: How do I pass CB Insights tools to my LangChain agent?

Call the gettools() method on your MultiServerMCPClient. Pass that resulting list directly into your createagent setup. The agent automatically understands the schema for endpoints like getinvestor.

Q: How does LangChain handle CB Insights pagination?

The ReAct agent reads the response from listdealsbyorg and determines if it needs to fetch more pages. It executes follow-up calls autonomously until it gathers the requested data.

Build multi-step reasoning pipelines that query venture capital data directly through LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CB Insights MCP to LangChain

Create your Vinkius account to connect CB Insights to LangChain 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 CB Insights with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain venture data into ReAct agents

The CB Insights MCP Server feeds live startup funding rounds straight into your LangChain graphs. Your ReAct agent checks connectivity with `check_cbi_status` and immediately begins pulling market trends. It decides when to search for companies using `list_organizations` based on the previous step's output. You observe every token and latency metric in LangSmith while the agent works. When a user asks about a specific startup, the chain calls `get_organization` followed by `get_org_competitors` to build a complete market map. Output from the competitor search instantly becomes the input for the next node in your pipeline.

Build automated LangChain MCP Server pipelines

Tracking venture capital deals requires sequential logic that LangChain handles perfectly. You build a chain that triggers `list_deals` daily to find new funding events in specific sectors. The agent iterates through the results and executes `get_deal` for every transaction over a certain dollar amount. Connecting this data to other APIs in your graph happens automatically. The agent grabs the lead backer using `get_investor`, then pulls their entire historical thesis via `get_investor_portfolio`. You map the entire private equity sector without writing custom API wrappers.

Route complex queries to native AI

Sometimes you need the proprietary business intelligence engine to do the heavy lifting before LangChain processes the result. Your agent can route high-level market questions directly to `chat_cbi`. The native engine analyzes the emerging tech trends and returns structured insights. Your custom chain then takes over to verify the claims. It parses the returned industries and runs `list_industries` to cross-reference the data. The final output delivered to your vector store contains both the high-level analysis and the hard funding numbers pulled via `get_org_funding`.

Setup guide

Set up CB Insights MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes CB Insights tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "cb-insights-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent CB Insights transactions"
    })
    print(result["messages"][-1].content)

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 CB Insights. 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 CB Insights 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 CB Insights MCP in LangChain

Call the get_tools() method on your MultiServerMCPClient. Pass that resulting list directly into your create_agent setup. The agent automatically understands the schema for endpoints like `get_investor`.

Yes. LangSmith tracks every interaction with the MCP Server. You see the exact inputs sent to `get_deal` and the resulting latency for the request.

You can combine this private market data with other internal APIs. Initialize the client with multiple server URLs and the agent will route requests to the correct destination.

The ReAct agent reads the response from `list_deals_by_org` and determines if it needs to fetch more pages. It executes follow-up calls autonomously until it gathers the requested data.

Vinkius isolates your session in a V8 sandbox. The funding amounts, competitor lists, and proprietary deal metrics you pull remain strictly in memory. The container destroys itself immediately after your LangGraph finishes execution.

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