How to Use the Clearstory MCP in LangChain

Q: How do I chain Clearstory tools in LangChain?

Use the MultiServerMCPClient to get the tools, then pass them to an agent executor like createagent. The agent will decide which Clearstory tool to call based on the prompt and the results of previous steps in the chain.

Q: Can my LangChain agent monitor multiple Clearstory projects?

Yes. Your agent can call listconstructionprojects to get a list of all active projects. From there, you can have it loop through the list to check the status, CORs, or T&M tags for each one.

Build agents that track construction projects and change orders. Step-by-step reasoning for your LangChain apps.

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 LangChain

Create your Vinkius account to connect Clearstory to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Project Data into Actionable Insights

Start by listing projects with `list_construction_projects`. Your agent can then pick a project and dive deeper, pulling contracts with `list_project_contracts` and then specific Change Order Requests using `list_change_order_requests`. It's a logical flow, not just a single API call. This is where LangChain shines. You can build a chain that first checks for new change notifications via `list_change_notifications`, then automatically fetches the full COR details with `get_cor_details` for any high-priority items. Your agent handles the multi-step logic on its own.

Automate Cost Analysis with this MCP Server

Give your agent the ability to check project financials. It can start with `list_construction_rates` to get the baseline Labor, Material, and Equipment rates for a job. This gives it the context needed for the next step. From there, the agent can cross-reference those rates against incoming Time & Material tags from the field using `list_tm_tags`. This lets you build agents that flag discrepancies between quoted rates and actuals, all within a single, traceable LangChain execution.

Build a Full-Scope Construction Bot

This isn't just about single tools; it's about composing them. You can design a ReAct agent that monitors an entire project's lifecycle. It starts with `get_project_construction_details` to get the big picture. Then, it can use the other Clearstory tools to react to changes. New T&M tag? `list_tm_tags`. New COR? `list_change_order_requests`. Your agent decides what to pull next based on the project's state, making it a dynamic part of your operations team.

Setup guide

Set up Clearstory MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Clearstory tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "clearstory-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Clearstory transactions"
    })
    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 LangChain

Use the `MultiServerMCPClient` to get the tools, then pass them to an agent executor like `create_agent`. The agent will decide which Clearstory tool to call based on the prompt and the results of previous steps in the chain.

Yes. Your agent can call `list_construction_projects` to get a list of all active projects. From there, you can have it loop through the list to check the status, CORs, or T&M tags for each one.

The Vinkius platform handles it. You just need your single endpoint token. The `langchain-mcp-adapters` library uses that token for all requests to the Clearstory MCP Server, so you don't manage credentials in your code.

Yes, it does. Every call your agent makes to a Clearstory tool like `get_cor_details` shows up in your LangSmith traces. You'll see the inputs, outputs, and latency for each step.

Your construction project data, including CORs and T&M tags, is passed through Vinkius's ephemeral, zero-trust environment. The data is only used for the duration of the API call and is not stored by Vinkius or LangChain.

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