How to Use the Supabase Vector MCP in CrewAI

Q: How can crewai agents perform vector searches using Supabase Vector?

You assign an agent role specifically to use matchvectors. The agent's tool definition points to the MCP Server, allowing it to run the search and surface results to its teammates.

Q: Does crewai support Supabase Vector for multi-agent research?

Yes. You can pipeline agents: Agent A researches using matchvectors, passes the IDs to Agent B, which then uses gettablerow to pull full records.

Q: How do I ensure data integrity when writing results back to Supabase Vector using crewai?

Always use callpostgresfunction for write operations. This lets you define a single, transactionally safe point where multiple agents commit their findings.

Q: If I need to clean up old vector data, how do I manage it with crewai?

You give the 'Custodian' agent permission to run deletetablerows. You must carefully script this role so that deletion only happens after all necessary steps are completed.

Build Autonomous Operations with Supabase Vector and crewai

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Supabase Vector MCP to CrewAI

Create your Vinkius account to connect Supabase Vector to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Supabase Vector with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agent Research via Semantic Search

Assign a 'Researcher' agent to use `match_vectors`. This agent executes the vector search against Supabase, retrieving contextually relevant documents. The results are then passed directly to the next specialized agent for analysis.

Data Analysis and Extraction

A separate 'Analyst' agent uses `get_table_row` to pull specific details from Supabase based on research findings. This allows you to break down a complex search result into actionable, structured data points.

Structured Data Population

After the agents complete their work, a final 'Writer' agent uses `insert_table_rows` to commit the compiled findings back into your Supabase table. This keeps your operational data clean and consistent.

Setup guide

Set up Supabase Vector 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 Supabase Vector tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Supabase Vector 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="Supabase Vector Analyst",
        goal="Access and analyze Supabase Vector data via MCP.",
        backstory="Expert analyst with direct Supabase Vector access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Supabase Vector 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 Supabase Vector. 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 Supabase Vector 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 Supabase Vector MCP in CrewAI

You assign an agent role specifically to use `match_vectors`. The agent's tool definition points to the MCP Server, allowing it to run the search and surface results to its teammates.

Yes. You can pipeline agents: Agent A researches using `match_vectors`, passes the IDs to Agent B, which then uses `get_table_row` to pull full records.

The framework's shared memory helps. If one agent fails its tool call (e.g., `match_vectors`), the monitor agent can log the error and prevent subsequent agents from running with bad data.

Always use `call_postgres_function` for write operations. This lets you define a single, transactionally safe point where multiple agents commit their findings.

You give the 'Custodian' agent permission to run `delete_table_rows`. You must carefully script this role so that deletion only happens after all necessary steps are completed.

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