How to Use the Aspire MCP in LlamaIndex

Q: How do I build a RAG app with Aspire and LlamaIndex?

Use the McpToolSpec to load the Aspire tools. Then, create a LlamaIndex agent that can call tools like listprojects and listposts. You can then either query live or index the results into a vector store for faster lookups.

Q: Can I use LlamaIndex to find top creators in my Aspire account?

Absolutely. You'd have an agent index the output of listprojectmembers and getmember. Then you can perform semantic searches across your entire creator database, asking questions like 'Find me creators who specialize in short-form video'.

Turn your Aspire campaign data into a searchable knowledge base with LlamaIndex. Ask questions, get answers grounded in facts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aspire MCP to LlamaIndex

Create your Vinkius account to connect Aspire 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 Aspire with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Creators and Campaigns

This server connects LlamaIndex directly to your Aspire marketing data. Your agent can call `list_projects` and `list_project_members` and feed the results straight into a vector index. Now you have a private, searchable database of all your campaigns and the creators who worked on them. Stop guessing who worked on what. You can ask your RAG application, 'Show me all creators who worked on the Q3 product launch' and get an immediate, accurate list. The data comes from `get_member` calls, indexed for instant retrieval.

Build a Campaign Performance Q&A Bot

Hook up the `list_posts` and `get_post` tools to a LlamaIndex agent. It will automatically pull and index engagement metrics for your social content. Your marketing team can then ask questions in plain English, like 'What was our most shared post in May?' or 'Compare the engagement of video vs. image posts for Project Firefly.' Your agent isn't just spitting back raw numbers. It's synthesizing information from the indexed Aspire data to give you real answers. This means fewer hallucinations and more trust in the output.

Live Data for Your LlamaIndex RAG App

Most RAG apps work with static documents. This MCP Server lets you augment your knowledge base with live data from Aspire. You can set up your LlamaIndex application to periodically refresh its index, ensuring your answers are always based on the latest campaign and content performance. There's no complex data pipeline to build. The `McpToolSpec` gives LlamaIndex a standardized way to call the tools and understand their output. It's the fastest way to ground your agent in your actual marketing operations.

Setup guide

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

Use the `McpToolSpec` to load the Aspire tools. Then, create a LlamaIndex agent that can call tools like `list_projects` and `list_posts`. You can then either query live or index the results into a vector store for faster lookups.

Absolutely. You'd have an agent index the output of `list_project_members` and `get_member`. Then you can perform semantic searches across your entire creator database, asking questions like 'Find me creators who specialize in short-form video'.

Grounding. Your agent's answers about campaign performance or creator history will be based on the actual data from your Aspire account that you've indexed, not on the LLM's general knowledge. This drastically reduces factual errors.

No, that's the whole point of indexing. You pull the data from Aspire once with tools like `list_campaigns`, index it, and then you can query that local index thousands of times without making new API calls. You can set up a schedule to refresh the index as needed.

Your LlamaIndex application will process your campaign project data, creator profiles, and post engagement stats. The MCP tool calls that fetch this data are executed in a zero-trust sandbox. Vinkius authenticates the request but has no visibility into the data itself, which is passed directly to your LlamaIndex agent.

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