How to Use the Keen MCP in AutoGen

Q: Can AutoGen agents collaborate to analyze Keen data?

Yes, one agent can run averageproperty while another uses the output to run a second query. They discuss the results in their chat history.

Q: How does AutoGen handle schema errors when querying Keen?

If selectunique fails due to a bad property name, the executing agent shares the error. Another agent checks listcollections to correct the schema.

Let your AutoGen agents debate metrics and write telemetry using the Keen MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keen MCP to AutoGen

Create your Vinkius account to connect Keen 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 Keen with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable AutoGen agents to debate Keen metrics

The `sum_property` tool provides the raw numbers for your agents to debate. A financial agent can run calculations while a marketing agent verifies volume, ensuring both agree before generating a report. If the numbers look off, an agent triggers the MCP tool `count_unique` to drill down into specific properties and resolve the discrepancy.

Automate telemetry verification via AutoGen debates

The `list_saved_queries` tool gives your agents a shared starting point. One agent retrieves the query definition, while another executes it to verify the payload is correct. They check for anomalies together. If a metric exceeds a threshold, they use `record_event` to log an alert directly back into your monitoring collection.

Inspect project metadata across agent conversations

The `get_project_details` tool allows your supervisor agent to verify connection parameters. It passes these details to worker agents so they know which collections to target. The workers then run `list_collections` to map the workspace. This coordinated approach keeps your multi-agent system aligned on the correct data sources.

Setup guide

Set up Keen 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 Keen 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="Keen_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the AutoGen MCP extension to fetch tools from the Vinkius endpoint. Pass the resulting tool list to your AssistantAgent constructor.

Yes, one agent can run `average_property` while another uses the output to run a second query. They discuss the results in their chat history.

If `select_unique` fails due to a bad property name, the executing agent shares the error. Another agent checks `list_collections` to correct the schema.

No, Vinkius hosts the server in a secure sandbox. Your agents connect via a single secure HTTP endpoint without any infrastructure setup.

Yes, your API keys and event metrics are stored securely on Vinkius and never shared with the LLM. The agents only see the high-level tools like `record_event`.

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