How to Use the Hasura (Instant GraphQL & REST Engine) MCP in Google ADK

Q: How do I connect the Google ADK to the Hasura (Instant GraphQL & REST Engine) MCP server?

You'll use the McpToolset from the Google ADK library, pointing it to the Vinkius server URL. Pass this toolset to your LlmAgent, and it will have access to all the Hasura tools like executegraphql.

Q: Can I use this to get data from Hasura into BigQuery?

Yes. Your Google ADK agent can use executegraphql to pull data from your Hasura-connected database and then use other native Google Cloud tools to pipe that data into a BigQuery table for large-scale analysis.

Q: Is it possible to limit which Hasura (Instant GraphQL & REST Engine) tools my Google ADK agent can use?

Yes, the McpToolset in the Google ADK has a toolnames filter. You can use it to expose only specific tools, like executegraphql, while hiding more sensitive ones like executemetadata or pgdump.

Connect your Google ADK agent to your Hasura (Instant GraphQL & REST Engine) to run queries and analyze data with Gemini's long-context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hasura (Instant GraphQL & REST Engine) MCP to Google ADK

Create your Vinkius account to connect Hasura (Instant GraphQL & REST Engine) to Google ADK 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 Hasura (Instant GraphQL & REST Engine) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Your Gemini Agent Real-Time Data

Let your Google ADK agent query your Postgres database directly through Hasura. The `execute_graphql` tool allows the agent to fetch exactly the data it needs, right when it needs it. No more stale data exports. This is perfect for agents that need to analyze current information. Gemini's large context window can handle the rich JSON responses from complex GraphQL queries, allowing for deep analysis of real-time database state.

Understand Query Performance

Don't let your agent run slow queries. The `explain_graphql` tool shows the underlying SQL execution plan that Hasura will run. Your agent can analyze this plan to identify bottlenecks or rewrite the query for better performance. This gives you a level of observability that's usually reserved for database administrators. Your agent can now make smart decisions about how it interacts with your database, preventing performance issues before they start.

Full Hasura Control with this MCP Server

This MCP server exposes more than just data access. Your agent can use `get_config` to see how the Hasura instance is configured or `check_health` to verify it's online. For maintenance tasks, tools like `pg_dump` let an agent create a database schema snapshot, and `execute_metadata` provides a direct interface to manage the Hasura schema itself. You can build agents that handle routine database maintenance on their own.

Setup guide

Set up Hasura (Instant GraphQL & REST Engine) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Hasura (Instant GraphQL & REST Engine) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Hasura (Instant GraphQL & REST Engine)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hasura (Instant GraphQL & REST Engine) tools via MCP.",
    tools=mcp_tools,
)

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 Hasura. 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 Hasura (Instant GraphQL & REST Engine) 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 Hasura (Instant GraphQL & REST Engine) MCP in Google ADK

You'll use the `McpToolset` from the Google ADK library, pointing it to the Vinkius server URL. Pass this toolset to your `LlmAgent`, and it will have access to all the Hasura tools like `execute_graphql`.

Yes. Your Google ADK agent can use `execute_graphql` to pull data from your Hasura-connected database and then use other native Google Cloud tools to pipe that data into a BigQuery table for large-scale analysis.

Yes, the `McpToolset` in the Google ADK has a `tool_names` filter. You can use it to expose only specific tools, like `execute_graphql`, while hiding more sensitive ones like `execute_metadata` or `pg_dump`.

It simplifies authentication and tool discovery. You get one Vinkius token for access, and the Google ADK integrates with the MCP standard, so you don't have to write custom wrappers for each Hasura API endpoint.

The MCP server is a managed endpoint, but you control the access. Your agent's interactions—including GraphQL queries and any data from `pg_dump`—are contained within your Google Cloud project's security context. You can run the server in your own VPC for maximum isolation.

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