How to Use the CB Insights MCP in AutoGen

Q: How do I connect the CB Insights tools to AutoGen?

Use mcpservertools with StreamableHttpServerParams. The McpToolAdapter automatically converts endpoints like getinvestor into schemas your AssistantAgent understands.

Q: Can AutoGen agents debate the CB Insights data?

That is the core feature. One agent pulls data using getorgfunding and proposes a valuation. A second agent reviews the same data, points out discrepancies, and forces a recalculation.

Deploy AutoGen multi-agent squads to debate and analyze venture capital trends.

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 AutoGen

Create your Vinkius account to connect CB Insights to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate market trends with AutoGen agents

The CB Insights MCP Server feeds raw financial data into your multi-agent conversations. You assign `list_deals` to a research agent that scours the market for recent funding rounds. A separate risk-analysis agent challenges the findings and demands more context. The agents negotiate the next steps autonomously. The researcher pulls specific transaction details using `get_deal` to defend its thesis. They continue debating the valuation metrics until they reach a consensus on the market direction.

Coordinate competitive analysis tasks

Evaluating a startup requires looking at the entire competitive field from multiple angles. One AutoGen agent executes `get_organization` to pull the core company profile. Another agent immediately runs `get_org_competitors` to find similar players in the space. The squad discusses the differences in funding strategies between the rivals. A financial agent triggers `get_org_funding` for each competitor to compare their runways. The final output to the user represents a synthesized, debated conclusion rather than a simple data dump.

Distribute MCP Server investor research

Mapping a venture capital firm takes too much time for a single prompt. You create an AutoGen system where agents divide the labor. The lead agent calls `list_investors` to find active funds in a specific sector and assigns them to worker agents. Each worker runs `get_investor_portfolio` on their assigned firm. They report their findings back to the group chat. The lead agent cross-references the portfolios and uses `chat_cbi` to generate a high-level summary of the investment patterns.

Setup guide

Set up CB Insights MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes CB Insights tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="CB Insights_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CB Insights data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="CB Insights_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CB Insights data")
    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 AutoGen

Use mcp_server_tools with StreamableHttpServerParams. The McpToolAdapter automatically converts endpoints like `get_investor` into schemas your AssistantAgent understands.

Yes. You can provide the tool list to specific agents in your group chat. A researcher agent might have access to `list_organizations` while a critic agent only has read-only access to the conversation.

The framework translates the MCP protocol natively. You do not need to write custom JSON schemas for complex endpoints like `list_deals_by_org`.

That is the core feature. One agent pulls data using `get_org_funding` and proposes a valuation. A second agent reviews the same data, points out discrepancies, and forces a recalculation.

Your credentials stay locked behind the Vinkius managed endpoint. The organization details, funding rounds, and competitor maps stream through a stateless sandbox. We wipe the execution environment the second your multi-agent conversation ends.

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