How to Use the Aconex MCP in LangChain

Q: How do I connect the Aconex MCP Server to LangChain?

Install langchain-mcp-adapters and use the MultiServerMCPClient pointing to your Vinkius endpoint to expose Aconex tools. You then fetch these tools and pass them to your agent initialization.

Q: Can a LangChain agent manage Aconex mailing groups?

Yes, the LangChain agent uses createmailinggroup and deletemailinggroup within its execution loops based on project parameters. It handles these operations based on the requirements defined in your chain's prompt.

Q: Can I trace Aconex tool calls made by LangChain in LangSmith?

Yes, every call to listprojects or searchprojectdirectory is logged as a tool run in your LangSmith dashboard. You get full visibility into the exact payloads, latency, and token usage for each action.

Chain Aconex project setup and user directories directly into LangChain pipelines to automate construction onboarding.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aconex MCP to LangChain

Create your Vinkius account to connect Aconex 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 Aconex with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Aconex Onboarding with LangChain

The `invite_user_to_project` tool triggers immediately when your LangChain agent processes a new subcontractor contract. Your LangChain agent runs the invitation flow, checks Aconex directory listings, and updates project access without human intervention. LangSmith traces every step of this multi-tool sequence run through the Aconex MCP server. You see exactly when LangChain triggers `create_user` and how the output feeds directly into the next chain link.

Verify Global Directory Records

The `search_global_directory` tool queries the main global database to verify subcontractor identity before your LangChain agent grants project access. This prevents duplicate accounts by running a real-time Aconex lookup before LangChain processes the next node. Your LangChain ReAct agent checks the Aconex search results and branches its logic based on the user's status. If the user doesn't exist, the LangChain pipeline routes to `create_user` to spin up the Aconex account instantly.

Clone Project Templates

The `copy_project` tool clones your standard construction templates to spin up new workspaces inside LangChain sequences. The MCP server handles the heavy lifting, letting your LangChain chain replicate Aconex folder structures. After cloning, the LangChain run pulls the schema via `get_register_schema` to verify Aconex metadata fields. This ensures your automated Aconex setups match your LangChain compliance steps from day one.

Setup guide

Set up Aconex 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 Aconex 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({
    "aconex-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 Aconex 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 Aconex. 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 Aconex 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 Aconex MCP in LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` pointing to your Vinkius endpoint to expose Aconex tools. You then fetch these tools and pass them to your agent initialization.

Yes, the LangChain agent uses `create_mailing_group` and `delete_mailing_group` within its execution loops based on project parameters. It handles these operations based on the requirements defined in your chain's prompt.

Your LangChain configuration manages rate limits through standard backoff wrappers around the Aconex tool calls. The server passes API errors directly back to the chain for clean error handling.

Yes, every call to `list_projects` or `search_project_directory` is logged as a tool run in your LangSmith dashboard. You get full visibility into the exact payloads, latency, and token usage for each action.

All communication runs through a zero-trust V8 sandbox on Vinkius, meaning your LangChain directory queries never persist. The MCP server only accesses the specific Aconex endpoints needed for your active session.

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