How to Use the Watershed Climate MCP in AutoGen

Q: How can AutoGen agents compare emissions measurements using Watershed Climate?

The agents use listmeasurements to pull raw activity values. They then debate which measurement type (e.g., Scope 1 vs. Scope 3) should be prioritized for review, using the results of these tools in their reasoning process.

Q: Can I use AutoGen to generate multiple reports with Watershed Climate?

Yes. The agents can cycle through listreports to identify all available output types (CDP, TCFD). They then call getreport for each ID, allowing the system to build a comprehensive understanding of all reporting options.

Q: What happens when I submit data using Watershed Climate and AutoGen?

The agent first calls validateupload. If successful, it submits via submitupload, which returns a task ID. A third agent can then monitor this task ID using gettaskstatus until the calculations are finished.

Run Deliberative Emissions Planning with AutoGen: Consensus-Driven Reporting via Watershed Climate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Watershed Climate MCP to AutoGen

Create your Vinkius account to connect Watershed Climate 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 Watershed Climate with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Define and Debate Reduction Targets

Use `list_reduction_targets` to see all configured organizational goals. This tool provides the baseline year, target percentage, and goal status. Multi-agent systems shine here: one agent can check current measurements via `list_measurements`, while another challenges that data against the targets returned by this MCP Server. The agents debate what adjustments are needed.

Manage Emissions Measurements

Call `get_inventory` to get detailed carbon footprint results for a specific scope and year. This process is essential for knowing exactly where emissions come from. To view the raw data that feeds into these totals, use `list_measurements`. The agent can compare measurement types (like electricity vs. shipping) across different years found via `list_inventories`.

Structure and Update Activity Data

You must start by calling `create_upload` to establish a data container. Once the upload ID is ready, agents can use `update_upload_data_record` or `upload_data_records` to correct or add activity inputs. This controlled process ensures that when the final agent runs `validate_upload`, all data points are accurate and ready for submission.

Setup guide

Set up Watershed Climate 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 Watershed Climate 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="Watershed Climate_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The agents use `list_measurements` to pull raw activity values. They then debate which measurement type (e.g., Scope 1 vs. Scope 3) should be prioritized for review, using the results of these tools in their reasoning process.

The MCP Server provides a set of external functions—the 'tools'—that agents can call. Instead of just talking, they execute code like `get_task_status` or `list_reports`, making the decision-making process concrete and verifiable.

Yes. The agents can cycle through `list_reports` to identify all available output types (CDP, TCFD). They then call `get_report` for each ID, allowing the system to build a comprehensive understanding of all reporting options.

The agent first calls `validate_upload`. If successful, it submits via `submit_upload`, which returns a task ID. A third agent can then monitor this task ID using `get_task_status` until the calculations are finished.

This server manages activity data records and emissions measurements. These specific values, representing actual carbon footprint inputs, are what your system will read and process for Watershed Climate reporting.

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