How to Use the Directus MCP in LlamaIndex

Q: How does LlamaIndex index Directus collection schemas?

The framework uses McpToolSpec to load the listcollectionfields tool. It executes the tool, retrieves the column configurations, and writes them directly into your vector index for semantic querying.

Q: Can I use LlamaIndex to search through Directus files?

Yes, by calling listdirectusfiles through the MCP Server. LlamaIndex indexes the returned file metadata, letting you search your media storage assets using natural language queries.

Q: How do I set up the Directus MCP integration in LlamaIndex?

Install llama-index-tools-mcp and initialize the client with your Vinkius endpoint. Pass the tools array to your FunctionAgent to start querying database records.

Q: Can the agent update database records during a RAG session?

Yes, the agent uses listcollectionitems to locate specific records before invoking patchcmsrecord to modify target database values.

Index Directus database schemas and records into LlamaIndex vector stores using this 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 Directus MCP to LlamaIndex

Create your Vinkius account to connect Directus 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 Directus with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Directus schemas with this MCP Server

By calling the `list_schema_collections` tool, LlamaIndex pulls structural rules defining your PostgreSQL tables. The framework indexes this metadata, allowing your agent to locate the correct table through semantic search instead of hardcoded lookups. This eliminates manual mapping. When you ask a question about your database structure, LlamaIndex queries the indexed schema rules to find the right collection instantly.

Ground RAG pipelines in live database records

Retrieving explicit cloud logging tracing specific database row UUIDs, the `get_single_item` tool feeds raw JSON payloads directly into your index. LlamaIndex ingests this raw payload, converting live database rows into searchable document nodes. Your agent searches these nodes to answer queries with real-time data. This prevents hallucinations by grounding every response in current database records rather than outdated training data.

Audit storage and users via vector search

With the `list_directus_files` tool, your LlamaIndex agent extracts metadata verifying your media storage configurations. Your agent indexes this file metadata alongside user directories fetched via `list_directus_users`. You can then query your vector store to find which admin identities manage specific media assets. The framework links these disparate data points into a single queryable index.

Setup guide

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

The framework uses `McpToolSpec` to load the `list_collection_fields` tool. It executes the tool, retrieves the column configurations, and writes them directly into your vector index for semantic querying.

Yes, by calling `list_directus_files` through the MCP Server. LlamaIndex indexes the returned file metadata, letting you search your media storage assets using natural language queries.

Install `llama-index-tools-mcp` and initialize the client with your Vinkius endpoint. Pass the tools array to your `FunctionAgent` to start querying database records.

Yes, the agent uses `list_collection_items` to locate specific records before invoking `patch_cms_record` to modify target database values.

All database records and schema schemas are processed inside ephemeral, zero-trust sandboxes. Your credentials and raw data are never cached or exposed to third-party indexing services.

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