Can the AI run write or drop queries?

That depends on your token's permissions. The `execute_query` tool passes any SQL to Starburst. To prevent mutations, provision a read-only token via your Starburst security settings.

How do I handle queries that return thousands of rows?

Always add a `LIMIT` clause in your SQL. Large result sets can exceed the AI's context window. Instruct the agent to use `LIMIT 10` or `LIMIT 50` to keep responses manageable.

What credentials do I need?

Two values: `STARBURST_HOST` (your cluster URL, e.g., `https://mycluster.trino.galaxy.starburst.io`) and `STARBURST_TOKEN` (a service account token from your Starburst admin settings).

Starburst MCP Server for CrewAI 6 tools — connect in under 2 minutes

Name: Starburst
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 6 Tools Framework

Connect your CrewAI agents to Starburst through the Vinkius — pass the Edge URL in the `mcps` parameter and every Starburst tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Starburst Specialist",
    goal="Help users interact with Starburst effectively",
    backstory=(
        "You are an expert at leveraging Starburst tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Starburst "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 6 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Starburst MCP Server

Integrate the powerful federated data analytics capabilities of Starburst directly into your conversational AI workflows. Empower your data engineering and analytics teams to query extensive data lakes, manage organizational roles, and explore detailed schemas without needing to explicitly switch between database clients. Securely map your AI assistant to your Starburst host, enabling natural language orchestration of complex Trino-based data products to accelerate data discovery and governance across your entire enterprise architecture.

When paired with CrewAI, Starburst becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Starburst tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

Federated Query Execution — Pass complex SQL statements programmatically against your connected data sources utilizing execute_query, receiving structured analytic returns directly.
Schema & Catalog Discovery — Actively map your data landscape by inspecting linked databases invoking list_catalogs, and drill down into specific table hierarchies using list_schemas.
Data Product Management — Manage and retrieve existing analytical data products across the Starburst network systematically validating data definitions using list_data_products.
Governance & Role Administration — Inspect access control limitations securely by navigating role assignments formally deploying requests through list_roles and evaluating privilege thresholds.

The Starburst MCP Server exposes 6 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Starburst to CrewAI via MCP

Follow these steps to integrate the Starburst MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 6 tools from Starburst

Why Use CrewAI with the Starburst MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Starburst through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Starburst + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Starburst MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Starburst for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Starburst, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Starburst tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Starburst against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Starburst MCP Tools for CrewAI (6)

These 6 tools become available when you connect Starburst to CrewAI via MCP:

get_query_details

Retrieves details for a specific SQL query

list_catalogs

g., S3, Snowflake, Iceberg) are connected. Lists all data catalogs available in Starburst Galaxy

list_data_products

Lists all published data products

list_domains

Lists data product domains

list_queries

Lists recent SQL queries executed in the cluster

list_roles

Lists all security roles in the organization

Example Prompts for Starburst in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Starburst immediately.

"List all active operational catalogs across the current data lake instance, and fetch the underlying schematics of any source containing the designation 'finance' in its structure."

"Execute a query to retrieve the top 10 rows from the 'customer_analytics' table located in our 'production_hive' catalog."

"List all registered data products across the Starburst network and check current role assignments to ensure proper access."

Troubleshooting Starburst MCP Server with CrewAI

Common issues when connecting Starburst to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Starburst + CrewAI FAQ

Common questions about integrating Starburst MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.