How to Use the Clearstory MCP in AutoGen

Q: How do I give different AutoGen agents access to different Clearstory tools?

When you create each AssistantAgent, you pass a specific tools list to its constructor. You can give a 'Finance' agent only the listconstructionrates tool, while a 'Project' agent gets listconstructionprojects and getcordetails.

Q: What does the setup for Clearstory and AutoGen look like?

You'll install autogen-extmcp. Then, use the mcpservertools function with your Vinkius server URL to get a list of tools. You can then assign this full list, or a subset of it, to your agents.

Q: Does this Clearstory MCP Server support streaming for AutoGen?

Yes. The autogen-ext supports the Streamable HTTP transport. This allows for real-time, token-by-token conversations between your agents as they work with Clearstory data.

Let your AutoGen agents debate and decide the best way to manage Clearstory projects. Build consensus on change orders and costs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clearstory MCP to AutoGen

Create your Vinkius account to connect Clearstory 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 Clearstory with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Have Agents Collaborate on Project Data

Set up a team of agents to analyze a project. A "ProjectManager" agent can call `get_project_construction_details` to get the overview. A "Finance" agent can simultaneously use `list_construction_rates` to check the budget. They then discuss their findings. The ProjectManager might see a new T&M tag via `list_tm_tags`, and the Finance agent can immediately cross-reference the cost. This isn't one agent following a script; it's a conversation to find issues.

Debate and Approve Change Orders

This MCP Server provides the facts for an agent debate. When a new COR appears from `list_change_order_requests`, one agent can pull the specifics with `get_cor_details`. Another agent, representing the client, can check the associated contract with `list_project_contracts`. They then debate the validity and cost of the COR. "Is this covered by the original contract?" "Does the cost align with our standard rates?" AutoGen lets them argue it out, using data from the Clearstory tools as their evidence, before presenting a final recommendation.

A Proactive Operations Team of Agents

Go beyond simple data retrieval. Create a team where one agent's job is to constantly monitor `list_change_notifications`. When it finds something, it alerts a "Reviewer" agent. The Reviewer agent then pulls the full context using other Clearstory tools and starts a conversation with a "Superintendent" agent to decide on a course of action. This multi-agent system turns passive data into an active, conversational workflow.

Setup guide

Set up Clearstory 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 Clearstory 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="Clearstory_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

When you create each `AssistantAgent`, you pass a specific `tools` list to its constructor. You can give a 'Finance' agent only the `list_construction_rates` tool, while a 'Project' agent gets `list_construction_projects` and `get_cor_details`.

Yes, that's the core idea. You can have multiple agents in a group chat. One agent can call `list_construction_projects`, post the result to the chat, and another agent can then use a project ID from that list to get more details.

You'll install `autogen-ext[mcp]`. Then, use the `mcp_server_tools` function with your Vinkius server URL to get a list of tools. You can then assign this full list, or a subset of it, to your agents.

Yes. The `autogen-ext` supports the Streamable HTTP transport. This allows for real-time, token-by-token conversations between your agents as they work with Clearstory data.

Your sensitive construction data, like contracts and LMEO rates, is processed in an isolated Vinkius sandbox for each tool call. AutoGen agents only receive the results of the call; the raw data isn't stored or logged by the Vinkius platform.

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