How to Use the Bloomreach MCP in AutoGen

Q: How do AutoGen agents share Bloomreach tool outputs?

When an agent calls listcampaigns, the resulting JSON payload is posted directly into the group chat context. All other agents in the AutoGen conversation can immediately read and analyze this data.

Q: How does AutoGen handle errors from a Bloomreach tool call?

If a tool like getcatalogitems fails, the error message is returned as agent feedback in the conversation. The AutoGen agents then discuss the error and attempt to correct the parameters for a retry.

Q: How does AutoGen protect customer properties during multi-agent runs?

Your customer data retrieved via getcustomerproperties is restricted to the local execution environment of your AutoGen runner. This MCP Server secures the transport layer with token-based authentication, ensuring raw profile data never leaks to external party servers.

Run multi-agent debates in AutoGen to optimize Bloomreach campaigns and customer segments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bloomreach MCP to AutoGen

Create your Vinkius account to connect Bloomreach 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 Bloomreach with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Bloomreach campaign performance in AutoGen

The `list_campaigns` tool lets your AutoGen marketing agent pull active campaigns into a group chat for immediate review. Using this MCP Server, a separate critic agent analyzes the campaign list to find inactive or redundant setups. This collaborative debate ensures that campaigns are scrutinized from multiple angles before any changes are proposed. Your agents use the raw campaign data to negotiate which marketing efforts require immediate budget adjustments.

Resolve customer segment conflicts via AutoGen agents

The `list_segments` tool provides the exact definitions your AutoGen agents need to discuss targeting overlaps. One agent can pull segment properties using `list_segmentations` while another checks for duplicate customer traits. By forcing your agents to reach a consensus on audience definitions, you prevent overlapping marketing messages. The final negotiated segment plan is output directly to your terminal.

Audit Bloomreach webhooks using AutoGen conversations

Your technical AutoGen agent calls `list_webhooks` to inspect active integration endpoints during system diagnostics. A security agent in the same conversation reviews these endpoints to flag unauthorized or broken URLs. This automated audit loop ensures that webhooks are validated by specialized agent personas before deployment. You get a clear log of the discussion and the final approved webhook list.

Setup guide

Set up Bloomreach 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 Bloomreach 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="Bloomreach_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

When an agent calls `list_campaigns`, the resulting JSON payload is posted directly into the group chat context. All other agents in the AutoGen conversation can immediately read and analyze this data.

Yes, you register the MCP Server tools only with specific executor agents in your AutoGen setup. This prevents critic or planner agents from directly calling tools like `get_customer_properties`.

If a tool like `get_catalog_items` fails, the error message is returned as agent feedback in the conversation. The AutoGen agents then discuss the error and attempt to correct the parameters for a retry.

Yes, you can stream tool results through the Streamable HTTP transport adapter. This allows your agents to process large lists of catalogs or campaigns chunk by chunk during active debates on the MCP.

Your customer data retrieved via `get_customer_properties` is restricted to the local execution environment of your AutoGen runner. This MCP Server secures the transport layer with token-based authentication, ensuring raw profile data never leaks to external party servers.

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