How to Use the Capacities MCP in LlamaIndex

Q: Can LlamaIndex query multiple Capacities spaces?

Yes, the agent can call listspaces to discover all available containers. It can then iterate through them, pulling nodes from each space to build a unified index.

Q: How does LlamaIndex handle media files from Capacities?

The agent uses savemedia to attach relevant images or documents directly to your records. LlamaIndex can then reference these attachments when generating responses that require visual context.

Index your Capacities knowledge graph directly into LlamaIndex vector stores using our managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capacities MCP to LlamaIndex

Create your Vinkius account to connect Capacities 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 Capacities with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index your entire graph structure for LlamaIndex RAG

The `get_structures` tool exposes your workspace definitions to your indexing pipelines over an MCP connection. LlamaIndex reads these schemas to understand how your notes are organized, allowing it to build a more accurate vector index of your custom object types. Your agent can then run `get_space_info` to map out the entire workspace configuration. This ensures that when you query your index, the retrieval engine respects the original taxonomy of your notes.

Build searchable indexes from live workspace nodes

The `get_object` tool fetches the raw text and property data of individual nodes so LlamaIndex can parse them into document chunks. Your index stays grounded in your actual notes, bypassing the need for manual exports or file conversions. When performing a semantic search, your agent runs `lookup` to find relevant nodes by title. It then pulls the full content of those nodes to construct a highly relevant context window for your LLM via the MCP Server.

Write retrieved web data back to your workspace

The `save_weblink` tool lets your LlamaIndex agent store newly discovered web resources directly into your graph. As the agent crawls web search results during a query, it saves the URLs as structured objects for later indexing. To document the search process, the agent uses `save_to_daily_note` to write an activity log. This leaves a clear trail in your daily journal explaining which sources were indexed and why.

Setup guide

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

Install llama-index-tools-mcp and initialize the BasicMCPClient with your Vinkius endpoint. Wrap it in an McpToolSpec and call to_tool_list_async to pass the tools to your FunctionAgent.

Yes, the agent can call `list_spaces` to discover all available containers. It can then iterate through them, pulling nodes from each space to build a unified index.

The agent uses `save_media` to attach relevant images or documents directly to your records. LlamaIndex can then reference these attachments when generating responses that require visual context.

Yes, all tool calls are fully compatible with LlamaIndex's async agent loop. This prevents blocking your main application thread when fetching large graph structures.

Vinkius manages your API credentials in a zero-trust, ephemeral gateway. Your actual workspace tokens, web links, and space metadata are never exposed to the LlamaIndex client or your local environment.

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