How to Use the Supabase Vector MCP in Pydantic AI

Q: How do I run a vector search with Supabase Vector and Pydantic AI?

You call matchvectors. The power here is that the response data is validated against your defined schema, guaranteeing clean, predictable output for your application logic.

Q: Does Supabase Vector support complex operations with Pydantic AI?

Yes. The server exposes multiple tools like callpostgresfunction and deletetablerows, all of which are managed through a type-safe interface, giving you confidence in the operation.

Run validated vector searches and reliable database writes with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Supabase Vector to Pydantic AI — 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate vector search results using `match_vectors`

The agent performs a semantic lookup via `match_vectors`, but because of the Pydantic wrapper, you get structured data back. If the API returns unexpected fields, the process fails loudly—no silent corruption. This guarantees that the embeddings and results passed to your application meet strict type definitions.

Ensure correct writes with `insert_table_rows`

When you use `insert_table_rows`, Pydantic validates the structure of the JSON array *before* it hits the database. This means your write operation is type-safe from start to finish. It’s a huge guardrail against bad input data messing up your schema.

Retrieve and validate single rows via `get_table_row`

Need one record? Use `get_table_row`. The Pydantic layer ensures that the returned row matches its expected model. If a column is missing or wrong, you fail fast. This makes it ideal for critical read paths where correctness matters more than speed.

Setup guide

Set up Supabase Vector MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "supabase-vector-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Supabase Vector tools.",
)

result = await agent.run("List recent Supabase Vector transactions")
print(result.output)

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 Pydantic AI

You call `match_vectors`. The power here is that the response data is validated against your defined schema, guaranteeing clean, predictable output for your application logic.

You can. Every interaction with the MCP Server—whether reading or searching—is validated by Pydantic models at runtime. It prevents hallucinated fields and ensures data integrity.

The agent executes the query, but before you get the results, Pydantic validates them. You'll only receive data that matches your expected structure.

Yes. The server exposes multiple tools like `call_postgres_function` and `delete_table_rows`, all of which are managed through a type-safe interface, giving you confidence in the operation.

The server handles standard relational database types plus high-dimensional vector embeddings. Pydantic ensures that both are correctly typed and validated upon retrieval.

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