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

Q: How do I configure the Hasura (Instant GraphQL & REST Engine) for a CrewAI agent?

Pass the endpoint URL directly into the mcps array when defining your agent. CrewAI automatically discovers all seven tools.

Q: Can I restrict which Hasura (Instant GraphQL & REST Engine) tools a CrewAI agent can use?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. This lets you give one agent executegraphql while restricting pgdump to an admin agent.

Q: How does CrewAI monitor Hasura (Instant GraphQL & REST Engine) uptime?

Assign a monitor agent the checkhealth tool. It can run periodic checks with strict mode enabled to verify metadata consistency and trigger alerts if the server fails.

Q: Can agents read the current server configuration?

They can. The getconfig and getversion tools return the exact Hasura server settings, allowing agents to adapt their behavior based on the live environment.

Q: How is sensitive data protected during a CrewAI pgdump operation?

The pgdump tool pulls your entire database schema and raw table contents. This MCP Server operates strictly within an isolated V8 sandbox, ensuring no residual data persists on our infrastructure after the Python client disconnects.

Deploy autonomous database administration teams with the Hasura (Instant GraphQL & REST Engine) MCP Server for CrewAI.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate CrewAI Database Teams

The `execute_graphql` tool gives your CrewAI agents direct read and write access to your Postgres database through Hasura. A research agent can run batched queries to gather user data, while an execution agent runs mutations to update records based on the findings. Everything happens autonomously. You define the schema, hand the MCP Server tools to the crew, and let them handle the sequential data processing without human intervention.

Optimize SQL Execution Plans

The `explain_graphql` tool allows a specialized database administrator agent to analyze slow queries. The agent requests the execution plan, reads the generated SQL, and identifies missing indexes or inefficient joins. It then feeds this analysis back to the developer team or uses it to rewrite the GraphQL request entirely. The entire optimization cycle occurs within the shared memory of the crew.

Automate Postgres Backups

The `pg_dump` tool lets a maintenance agent trigger full database backups on a schedule. The agent connects to the Postgres source, executes the dump, and retrieves the raw SQL output. Another agent can then take that output and push it to secure storage. You build a complete disaster recovery pipeline using just one tool command.

Setup guide

Set up Hasura (Instant GraphQL & REST Engine) 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 Hasura (Instant GraphQL & REST Engine) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Hasura (Instant GraphQL & REST Engine) 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="Hasura (Instant GraphQL & REST Engine) Analyst",
        goal="Access and analyze Hasura (Instant GraphQL & REST Engine) data via MCP.",
        backstory="Expert analyst with direct Hasura (Instant GraphQL & REST Engine) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Hasura (Instant GraphQL & REST Engine) 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 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 CrewAI

Pass the endpoint URL directly into the `mcps` array when defining your agent. CrewAI automatically discovers all seven tools.

Yes. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. This lets you give one agent `execute_graphql` while restricting `pg_dump` to an admin agent.

Assign a monitor agent the `check_health` tool. It can run periodic checks with strict mode enabled to verify metadata consistency and trigger alerts if the server fails.

They can. The `get_config` and `get_version` tools return the exact Hasura server settings, allowing agents to adapt their behavior based on the live environment.

The `pg_dump` tool pulls your entire database schema and raw table contents. This MCP Server operates strictly within an isolated V8 sandbox, ensuring no residual data persists on our infrastructure after the Python client disconnects.

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