How to Use the Aconex MCP in LlamaIndex

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

Install llama-index-tools-mcp and initialize the MCP client with your Vinkius URL. You then convert the Aconex tools using McpToolSpec and pass them to your LlamaIndex function agent.

Q: Can LlamaIndex index Aconex document schemas?

Yes, the LlamaIndex framework calls getregisterschema to retrieve the document structure. It then embeds this schema into your vector store, allowing the agent to reference correct Aconex metadata fields.

Q: How does LlamaIndex prevent stale data when querying Aconex?

You can set up a LlamaIndex refresh pipeline that calls listprojects and searchglobaldirectory on a schedule. This keeps your local vector index synchronized with real-time Aconex changes.

Index your Aconex directories and project schemas directly into LlamaIndex vector stores for semantic search without hallucinations.

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 LlamaIndex

Create your Vinkius account to connect Aconex to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic Search on Aconex Directories

The `search_project_directory` tool extracts user records and project metadata to build a local LlamaIndex vector index. LlamaIndex queries this index to find the right Aconex contractors based on semantic meaning rather than exact keyword matches. This setup prevents your LlamaIndex agent from hallucinating Aconex contact details during project coordination. The indexed results keep your queries grounded in real directory data.

Parse Project Schemas with an MCP Server

The `get_register_schema` tool pulls document structures directly into your LlamaIndex knowledge base via the MCP server. Your LlamaIndex pipeline indexes these schemas so the agent understands the exact Aconex metadata requirements. When you need to upload or verify files, the LlamaIndex agent queries the indexed Aconex schema first. This ensures all subsequent document actions comply with your project's specific folder rules.

Map Organization Users to Context

The `list_organization_users` tool fetches your complete internal roster to feed your LlamaIndex RAG pipeline. LlamaIndex processes this list, mapping Aconex roles and permissions to your contextual search index. When users ask about project assignments, the LlamaIndex agent pulls from this local vector store. This approach keeps your Aconex queries fast without hitting the live API for every single question.

Setup guide

Set up Aconex MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Aconex MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Aconex tools.",
)
response = await agent.run("List recent Aconex data")

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 LlamaIndex

Install `llama-index-tools-mcp` and initialize the MCP client with your Vinkius URL. You then convert the Aconex tools using `McpToolSpec` and pass them to your LlamaIndex function agent.

Yes, the LlamaIndex framework calls `get_register_schema` to retrieve the document structure. It then embeds this schema into your vector store, allowing the agent to reference correct Aconex metadata fields.

You can set up a LlamaIndex refresh pipeline that calls `list_projects` and `search_global_directory` on a schedule. This keeps your local vector index synchronized with real-time Aconex changes.

Yes, you can combine this server with other data sources in LlamaIndex. Your agent can query your internal database and then use `invite_user_to_project` to sync Aconex users.

The index runs locally in your environment, and Vinkius secures the data transit through our MCP gateway. Your Aconex document register schemas are never stored on external servers or used to train public models.

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