How to Use the Clearstory MCP in LlamaIndex

Q: How can I use LlamaIndex to search Clearstory CORs?

Use the McpToolSpec to load the Clearstory tools. Have your agent call listchangeorderrequests and index the results into a vector store. You can then use a LlamaIndex query engine to search the indexed COR data.

Q: What's the setup for Clearstory and LlamaIndex?

It's straightforward. After pip install llama-index-tools-mcp, you create a BasicMCPClient with your Vinkius URL. Then, wrap it in McpToolSpec and you're ready to add the tools to your agent.

Turn Clearstory project data into a searchable knowledge base for your LlamaIndex RAG apps. Get answers grounded in reality.

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 LlamaIndex

Create your Vinkius account to connect Clearstory 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 Clearstory with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Queryable Project Index

Use the Clearstory tools to pull live data, and let LlamaIndex do the rest. Run `list_construction_projects` and `list_project_contracts` to fetch all your core project information. LlamaIndex will automatically index this content into a vector store. Now you can ask questions in natural language, like "What contracts are associated with the downtown tower project?" Your RAG application will query the index of actual project data to give you an answer, not just guess.

Your RAG App, Powered by this MCP Server

Stop digging through emails for change order details. Connect this MCP server and have your agent periodically call `list_change_order_requests` and `get_cor_details`. LlamaIndex will ingest and vectorize the results. This creates a living knowledge base of all your CORs. You can then build a query engine to ask things like "show me all CORs over $10k from last month" or "what was the reason for COR-1138?". Your agent finds the answer in the data it indexed.

Ground Answers in Financials

This is how you stop hallucinations about project costs. Use the `list_construction_rates` and `list_tm_tags` tools to feed real-time financial data into your LlamaIndex vector store. When you ask your agent "what's our standard labor rate for electricians?" or "find all T&M tags submitted by Jane Doe last week," it retrieves the answer directly from the indexed results of those tool calls. It's not making things up; it's reporting on the data you fed it.

Setup guide

Set up Clearstory 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 Clearstory 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 Clearstory tools.",
)
response = await agent.run("List recent Clearstory 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 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 LlamaIndex

Use the `McpToolSpec` to load the Clearstory tools. Have your agent call `list_change_order_requests` and index the results into a vector store. You can then use a LlamaIndex query engine to search the indexed COR data.

Absolutely. That's what it's for. You can index data from the Clearstory MCP Server alongside your own PDFs, docs, or other data sources into a single, unified index for your RAG application.

You control the refresh rate. You can set up your LlamaIndex application to periodically call the Clearstory tools, like `list_change_notifications`, and re-index the results. This keeps your knowledge base current with the live project data.

It's straightforward. After `pip install llama-index-tools-mcp`, you create a `BasicMCPClient` with your Vinkius URL. Then, wrap it in `McpToolSpec` and you're ready to add the tools to your agent.

When LlamaIndex calls a tool, your project and change order data passes through the Vinkius sandbox for that request only. You control where the indexed data is stored—in your own vector database or locally. Vinkius itself doesn't retain any of your Clearstory data.

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