How to Use the Capsule CRM MCP in AutoGen

Q: How do I configure AutoGen to use Capsule CRM?

Use mcpservertools with a StreamableHttpServerParams configuration pointing to your Vinkius URL. Pass the resulting tool list directly into your AssistantAgent constructor.

Give your AutoGen agents direct access to Capsule CRM. Let them debate sales strategies based on live pipeline data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capsule CRM MCP to AutoGen

Create your Vinkius account to connect Capsule 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 Capsule CRM with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent CRM Operations

Single agents make mistakes. You build a system where a research agent pulls `get_contact_details` while a sales agent reviews the output. They talk to each other before deciding how to proceed. This conversational approach catches errors. If the sales agent suggests an aggressive pitch, the research agent might flag a recent support ticket found in the account history and push back. They negotiate the best approach.

Automate Task Creation via MCP Server

Reaching consensus is only half the battle. Once your agents agree on a plan, they need to execute it. One agent takes the lead and fires `create_task` to assign the agreed-upon action items to your human team. They can also register new leads during the discussion. If a marketing agent identifies a hot prospect, it triggers `create_person` immediately. The system acts on decisions the second they are made.

Analyze Project Delivery

You can assign specific roles to different bots. A project management agent constantly polls `list_projects` and `get_project_details` to monitor delivery timelines. When that agent spots a delay, it messages the account management agent. The account agent then runs `list_opportunities` to see if the delay threatens any upcoming renewals. They collaborate to solve the problem.

Setup guide

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

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

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

Use mcp_server_tools with a StreamableHttpServerParams configuration pointing to your Vinkius URL. Pass the resulting tool list directly into your AssistantAgent constructor.

They share the tool definitions, but each agent decides when to call them. You can give the list_contacts capability to a researcher while restricting the writer agent from accessing the API entirely.

McpToolAdapter translates the MCP Server definitions automatically. Your agents understand exactly what arguments create_task requires without any manual prompt engineering.

The Vinkius endpoint supports Streamable HTTP. You just drop the URL and auth token into your server parameters and the framework handles the connection lifecycle.

Every request runs through a zero-trust, ephemeral sandbox. When your agents debate deal sizes or project statuses, the API calls execute in isolated V8 environments that leave zero trace on our infrastructure.

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