How to Use the Tower MCP in LlamaIndex

Q: Can LlamaIndex query historical project data from Tower?

Absolutely. By indexing outputs from tools like listprojects and getproject, you build a RAG application where past configurations and metadata are searchable, avoiding hallucinations.

Q: What kind of documentation can LlamaIndex index using Tower?

It indexes the structure found by listdocfolders. You get a searchable map of the entire document hierarchy—the names, paths, and organization of your project assets.

Index project data and history with LlamaIndex and Tower MCP Server. Searchable knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tower MCP to LlamaIndex

Create your Vinkius account to connect Tower 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 Tower with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Project Metadata

The `list_projects` tool gives you all available projects, but LlamaIndex doesn't stop there. It indexes the project names and details into a searchable vector store. Later, you can query past sessions about specific projects and get answers grounded in actual API data, not just general knowledge.

Recall Discussions History

Use `list_discussions` to pull the details of project conversations. LlamaIndex makes these discussions part of a unified index, meaning you can query them semantically. You can ask about past decisions or who was involved in a specific discussion months ago and get an answer sourced directly from the tool output.

Index Document Structure

Call `list_doc_folders` to map out your document structure. LlamaIndex takes this folder list and indexes it, creating a searchable knowledge base of where all files live. This allows you to query the *structure* of documentation—for example, 'where are the Q4 reports for Project X'—and get an answer based on directory names.

Setup guide

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

LlamaIndex treats every tool output as a source of truth. When you call `get_task_details`, the resulting task information is indexed, allowing subsequent queries to reference that specific status or description.

Absolutely. By indexing outputs from tools like `list_projects` and `get_project`, you build a RAG application where past configurations and metadata are searchable, avoiding hallucinations.

It indexes the structure found by `list_doc_folders`. You get a searchable map of the entire document hierarchy—the names, paths, and organization of your project assets.

Instead of just reading the current status, you can query the history of tasks. If a user asks, 'What changed about Task XYZ last week?', LlamaIndex surfaces that historical data from its index.

The server touches Project Names, Document Folder Paths, Task Descriptions, Team Names, and Member Roles. These strings are chunked and stored as searchable knowledge.

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