How to Use the Upstream Lens MCP in AutoGen

Q: Can AutoGen use Upstream Lens to compare projects?

Yes. Give two competing agents access to listprojects and listpropertyimagery. They can 'debate' which project needs attention based on the combination of site existence and current imagery data.

Q: How do I determine the scope of available data with Upstream Lens and AutoGen?

Run two agents: one calls listprojects, and another calls listpropertyimagery. The subsequent debate identifies gaps, like 'We know the sites exist, but we need to confirm imagery layers for Site X.'

Drive consensus on site status using AutoGen with the 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 Upstream Lens MCP to AutoGen

Create your Vinkius account to connect Upstream Lens 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 Upstream Lens with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Facilitate decision-making via the MCP Server.

Set up a debate between two agents: one that uses `list_projects` to list all environmental sites, and another that calls `get_property_details`. They can argue about which site requires immediate attention based on different criteria. This forces consensus, making the final decision much stronger than any single API call.

Negotiate complex project status reports.

Use AutoGen to make agents challenge each other's findings. One agent calls `list_project_notes` for historical context, while a second agent uses `list_observations` to provide current data. The negotiation converges on the true operational status. The result is an agreed-upon conclusion derived from multiple inputs.

Determine asset scope through structured debate.

One agent can query `get_organization_info` for general metadata, while a second agent calls `list_portfolios`. They debate whether the current operational needs fall within established financial portfolios or if new funds are needed. The final output is not just data; it's an action plan agreed upon by multiple perspectives.

Setup guide

Set up Upstream Lens 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 Upstream Lens 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="Upstream Lens_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You can deploy a 'Validator Agent' whose sole job is calling `check_api_health` via the MCP Server. This agent reports its findings, which then feeds into a subsequent debate between resource allocation agents.

Yes. Give two competing agents access to `list_projects` and `list_property_imagery`. They can 'debate' which project needs attention based on the combination of site existence and current imagery data.

This MCP Server works with environmental project metadata (from `get_organization_info`) and structured asset details found in the outputs of `list_portfolios`. These two datasets form the core context for debate.

You can set up agents that argue over which properties need attention. They call `get_property_details` on specific features, simulating a board meeting consensus before any work starts.

Run two agents: one calls `list_projects`, and another calls `list_property_imagery`. The subsequent debate identifies gaps, like 'We know the sites exist, but we need to confirm imagery layers for Site X.'

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