How to Use the Dagster MCP in LlamaIndex

Q: Does LlamaIndex cache the output of Dagster tool calls?

Yes, you can configure LlamaIndex to store the results of listassets or listjobs in a vector index. This prevents redundant Dagster API calls and speeds up your LlamaIndex queries.

Q: Can I filter which Dagster tools are exposed to LlamaIndex?

Yes, use the allowedtools filter to expose only specific Dagster tools like listruns while hiding other tools from LlamaIndex.

Q: How does LlamaIndex handle large Dagster asset graphs?

LlamaIndex chunks the raw JSON output from listassets into node documents. This ensures large Dagster payloads fit within your LlamaIndex context window without losing metadata.

Index your live Dagster pipeline metadata into searchable LlamaIndex vector stores with 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 Dagster MCP to LlamaIndex

Create your Vinkius account to connect Dagster 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 Dagster with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a LlamaIndex RAG index from your Dagster assets

The `list_assets` tool retrieves your entire software-defined Dagster asset graph to populate your LlamaIndex vector index. Your LlamaIndex agent queries this index to answer complex questions about Dagster data lineage. LlamaIndex updates this knowledge base dynamically by calling the Dagster tool during indexing pipelines. You get answers grounded in actual, live Dagster asset definitions instead of outdated documentation.

Query active Dagster jobs using this MCP Server

The `list_jobs` tool extracts your Dagster pipeline structures, while `list_schedules` pulls the exact Dagster cron configurations into LlamaIndex. Your LlamaIndex agent parses this raw data to build an active timeline of your data platform. Instead of searching through the Dagster UI, you ask your LlamaIndex agent which Dagster jobs run on weekends. The LlamaIndex agent queries the indexed Dagster tool outputs to give you an instant schedule breakdown.

Monitor Dagster run histories in LlamaIndex

The `list_runs` and `list_sensors` tools feed live Dagster execution history and sensor states into your LlamaIndex context. Your LlamaIndex agent compares recent Dagster run durations to flag performance anomalies. Using `get_run`, the LlamaIndex agent drills down into specific Dagster run failures to extract error messages. It indexes these Dagster errors so you can search past failures using LlamaIndex semantic search.

Setup guide

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

Install llama-index-tools-mcp and initialize the BasicMCPClient with the Dagster URL. Wrap it in a McpToolSpec to expose the Dagster tools to your LlamaIndex FunctionAgent.

Yes, you can configure LlamaIndex to store the results of `list_assets` or `list_jobs` in a vector index. This prevents redundant Dagster API calls and speeds up your LlamaIndex queries.

Yes, use the allowed_tools filter to expose only specific Dagster tools like `list_runs` while hiding other tools from LlamaIndex.

LlamaIndex chunks the raw JSON output from `list_assets` into node documents. This ensures large Dagster payloads fit within your LlamaIndex context window without losing metadata.

Yes, your Dagster job configurations and run statuses are processed in memory within secure V8 isolates. Vinkius does not persist or inspect the Dagster data payloads passing through LlamaIndex.

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