How to Use the Evolio MCP in LlamaIndex

Q: How do I start using Evolio with LlamaIndex?

Install llama-index-tools-mcp and instantiate the BasicMCPClient with your endpoint URL. You'll wrap that in the McpToolSpec and call totoollistasync() to get tools for your agent.

Q: What's the best way to index Evolio client data in LlamaIndex?

Use the McpToolSpec to load all 14 tools. Create a FunctionAgent and give it a routine task, like 'Summarize all open cases'. The agent will call listcasesbystatus and getcase, and you can configure LlamaIndex to automatically index those results.

Q: Can a LlamaIndex agent create a new task in Evolio?

Yes. The createtask tool is available just like any other. Your agent can decide to call it based on the results of a query. For instance, if a query shows no activity on a case, the agent can create a follow-up task.

Turn your Evolio coaching data into a queryable knowledge base with LlamaIndex. Ask questions, get answers from your own data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evolio MCP to LlamaIndex

Create your Vinkius account to connect Evolio 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 Evolio with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Client Memory

LlamaIndex uses the Evolio tools to build a searchable index of your practice. It doesn't just call an API; it remembers the answer. Your agent can run `get_client`, `get_case`, and `list_tasks_by_case` and store the results. Later, you can ask, 'What were the last three tasks for Jane Doe?' LlamaIndex queries its internal index first, giving you an instant answer grounded in past API calls. You hit the live API only when you need fresh data.

Get a Complete Client Picture

This is for building RAG applications. You can combine structured data from Evolio with your own unstructured notes. Use the `list_client_files` tool to get a list of documents, and index their contents alongside data from `get_case` and `get_task`. Now, when you ask a question about a client's progress, your LlamaIndex agent pulls information from everywhere—API data, meeting notes, documents—to give you a single, complete answer. It connects the dots for you.

Query Your MCP Server's History

You can build an agent that periodically runs tools like `list_cases` and `list_clients` to create a historical index. This turns your operational data into a source for insights. The MCP server provides the live data, LlamaIndex provides the memory. A new coach could ask, 'Show me examples of cases that stalled in the first month.' Your agent can query the indexed history of `list_cases_by_status` calls to find the answer. It's a way to learn from your own experience.

Setup guide

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

Install `llama-index-tools-mcp` and instantiate the `BasicMCPClient` with your endpoint URL. You'll wrap that in the `McpToolSpec` and call `to_tool_list_async()` to get tools for your agent.

Not directly through this MCP server, as it only lists files with `list_case_files`. However, you can use that tool to get a file manifest, then use another LlamaIndex reader to ingest the actual file content into your index.

Use the `McpToolSpec` to load all 14 tools. Create a `FunctionAgent` and give it a routine task, like 'Summarize all open cases'. The agent will call `list_cases_by_status` and `get_case`, and you can configure LlamaIndex to automatically index those results.

Yes. The `create_task` tool is available just like any other. Your agent can decide to call it based on the results of a query. For instance, if a query shows no activity on a case, the agent can create a follow-up task.

When you use LlamaIndex, you're creating an index of your Evolio data—client names, case data, task contents. The security of that data depends entirely on where you store the index. The Evolio connection itself is secure, but the indexed copy is your responsibility.

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