How to Use the Enrich CRM MCP in AutoGen

Q: Can different AutoGen agents use different Enrich CRM tools?

Yes. You can configure your "researcher" agent to only use enrichcompany and enrichperson, while your "sales" agent only has access to findemail and findphone. This lets you create specialized roles.

Q: Can AutoGen agents debate the quality of data from Enrich CRM?

They can. You could program an agent to check if findphone returns a direct dial or a switchboard number. If it's a switchboard, it could flag the record and ask another agent to try a different approach.

Create teams of AI agents in AutoGen that debate and decide on the best sales targets together.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Enrich CRM MCP to AutoGen

Create your Vinkius account to connect Enrich CRM 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 Enrich CRM with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Prospecting

With AutoGen, you create a team of specialist agents that work together. A "Research" agent can use `enrich_company` to generate a list of potential targets. A "Qualifier" agent can then use `get_account_info` to check for existing relationships and argue against pursuing them. This isn't a simple script; it's a conversation. The agents debate the merits of each prospect, using data from the Enrich CRM tools as evidence in their arguments. The final target list is a product of their consensus.

Simulate Your Sales Team's Workflow

Model your real-world team in code. An "Outreach" agent can be tasked with finding contact info, using `find_email` and `find_phone`. A "Manager" agent can oversee the process, asking for progress reports and resolving disagreements between the other agents. This lets you automate complex decision-making. You're not just getting data; you're getting a recommendation that has been challenged and defended by multiple AI perspectives, all using this MCP server for ground truth.

An AutoGen MCP Server for Sales Ops

The Enrich CRM tools are exposed to your AutoGen agents using `mcp_server_tools`. Each agent in the group can be given access to all the tools, or just a subset. You could have a dedicated "Data" agent that is the only one allowed to call `enrich_person`. This allows for role-based task execution within your agent swarm. It mirrors how a real team operates, with different members responsible for different parts of the process. The result is a more organized and robust automation.

Setup guide

Set up Enrich CRM 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 Enrich CRM 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="Enrich CRM_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Enrich CRM 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="Enrich CRM_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Enrich CRM 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 Enrich CRM. 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 Enrich CRM 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 Enrich CRM MCP in AutoGen

You assign the Enrich CRM tools to your agents. One agent might use `enrich_company` to find targets, while another uses `find_email` to get contact info. They then talk to each other to complete the overall task.

Yes. You can configure your "researcher" agent to only use `enrich_company` and `enrich_person`, while your "sales" agent only has access to `find_email` and `find_phone`. This lets you create specialized roles.

Build an automated account-based marketing (ABM) team. Have one agent identify ideal customer profiles with `enrich_company`, another find key people with `enrich_person`, and a third plan the outreach sequence. They collaborate to build the entire campaign.

They can. You could program an agent to check if `find_phone` returns a direct dial or a switchboard number. If it's a switchboard, it could flag the record and ask another agent to try a different approach.

Each lookup is a discrete, stateless transaction. Data like a person's name or a company URL is sent for enrichment but is never stored on the server. Vinkius ensures your session is private and the data is only used to return your result.

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