How to Use the Metaplane MCP in LlamaIndex

Q: How do I load Metaplane tools into LlamaIndex?

Install llama-index-tools-mcp and initialize the MCP client with your server URL. Wrap it in a McpToolSpec and call totoollistasync to load the tools into your LlamaIndex FunctionAgent.

Q: Can LlamaIndex search through historical Metaplane runs?

Yes, LlamaIndex indexes the output from getmonitorruns into a vector store. This allows your RAG application to perform semantic search over past execution patterns and run durations.

Q: How does LlamaIndex handle Metaplane alerts?

Your LlamaIndex agent queries listconfiguredalerts to find active notification endpoints. It can then format and route data quality summaries directly to those destinations when a query detects an anomaly.

Q: How is my Metaplane schema data secured in LlamaIndex?

Only metadata like connection details from listdataconnections and monitor configurations from listmonitors are processed. No raw table data is ever read or stored in your LlamaIndex vector indexes.

Index Metaplane data health and schemas directly into your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metaplane MCP to LlamaIndex

Create your Vinkius account to connect Metaplane 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 Metaplane with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Metaplane schemas into LlamaIndex vector stores

Your LlamaIndex agent calls `list_connection_schemas` to pull your database structures and indexes them as vector embeddings for semantic search. This lets your RAG pipeline query your physical database layout using natural language, pointing users to the exact tables they need. By grounding your queries in real metadata from `list_data_connections`, you prevent your LLM from hallucinating table names or column types. The index stays updated by pulling fresh schema data whenever your scheduled pipelines run.

Query Metaplane incident history with LlamaIndex RAG

This MCP Server exposes `list_incidents` to let you build a searchable knowledge base of your data quality history inside LlamaIndex. When an engineer asks about past pipeline failures, the agent searches the indexed output of `get_incident` to find how similar issues were resolved. This transforms your raw incident logs into an active troubleshooting assistant. Instead of digging through Slack history, your team queries LlamaIndex to get immediate context on historical data drift and broken monitors.

Monitor data quality states via LlamaIndex agents

Your agent uses this MCP Server to invoke `list_monitors` to check the current health status of your data warehouse before executing critical semantic search queries. LlamaIndex uses this live observability data to determine if the underlying vector sources are reliable and fresh. If a monitor fails, the agent calls `get_monitor_runs` to assess the severity of the issue before serving answers to your users. This protects your production search applications from displaying outdated or corrupted information.

Setup guide

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

Install `llama-index-tools-mcp` and initialize the MCP client with your server URL. Wrap it in a `McpToolSpec` and call `to_tool_list_async` to load the tools into your LlamaIndex `FunctionAgent`.

Yes, LlamaIndex indexes the output from `get_monitor_runs` into a vector store. This allows your RAG application to perform semantic search over past execution patterns and run durations.

Your LlamaIndex agent queries `list_configured_alerts` to find active notification endpoints. It can then format and route data quality summaries directly to those destinations when a query detects an anomaly.

Yes, you can pass an allowed tools list to the MCP tool specification. This restricts your agent to safe read-only operations like `list_monitors` while blocking write operations like `trigger_monitor_run`.

Only metadata like connection details from `list_data_connections` and monitor configurations from `list_monitors` are processed. No raw table data is ever read or stored in your LlamaIndex vector indexes.

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