How to Use the Veraset MCP in CrewAI

Q: If an investigation with Veraset gets stuck, how do I stop it? (CrewAI)

You simply use the cancelrunningquery tool. This lets a moderator agent terminate any SQL task immediately, freeing up resources for a new line of inquiry.

Q: Does CrewAI need to check dataset definitions before querying Veraset?

Yes. Before running executesqlquery, the research agent should use getdatasetschema to verify column names and data types, which prevents failed queries.

Run autonomous Veraset data investigations with CrewAI specialized agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Veraset MCP to CrewAI

Create your Vinkius account to connect Veraset to CrewAI 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 Veraset with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Data Discovery

Specialized agents can collaborate on complex data tasks. One agent might call `list_mobility_datasets` to research sources, while another uses that list to plan the schema extraction via `get_dataset_schema`. The shared memory ensures all agents operate with the same, up-to-date information about Veraset's data landscape.

Executing and Monitoring Queries

A dedicated execution agent can run SQL via `execute_sql_query` and then pass the resulting query ID to a monitor agent. This second agent continuously checks progress using `get_query_status`. The system also allows for terminating tasks early with the `cancel_running_query` tool if the data quality is poor.

Managing Data Outcomes

The crew can execute a full cycle: fetching metadata using `get_dataset_metadata`, sampling it with `get_dataset_sample`, and finally, having an action agent retrieve results via `get_query_results`. This entire process keeps the analysis contained to Veraset's structured data.

Setup guide

Set up Veraset MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Veraset tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Veraset Analyst",
    goal="Access and analyze Veraset data via MCP.",
    backstory="Expert analyst with direct Veraset access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Veraset transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

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

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Veraset Analyst",
        goal="Access and analyze Veraset data via MCP.",
        backstory="Expert analyst with direct Veraset access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Veraset transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

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

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 Veraset. 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 Veraset 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 Veraset MCP in CrewAI

The system supports pagination for retrieval. The action agent uses `get_query_results` and passes the required page number, ensuring that massive datasets are handled in manageable chunks.

It handles mobility-focused assets. Agents start by calling `list_mobility_datasets` to identify all accessible pools, or they can check for scheduled drops using `list_s3_delivery_folders`.

You simply use the `cancel_running_query` tool. This lets a moderator agent terminate any SQL task immediately, freeing up resources for a new line of inquiry.

Yes. Before running `execute_sql_query`, the research agent should use `get_dataset_schema` to verify column names and data types, which prevents failed queries.

This MCP Server touches structured mobility dataset metadata. This includes technical definitions like column names and associated data types used in the database schema.

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