How to Use the Vald MCP in Pydantic AI

Q: How do I search for vectors with Vald and Pydantic AI?

Use searchvectors. You send it a query vector (a JSON array of floats), and the MCP Server performs the nearest neighbor lookup. The agent gets accurate context instantly.

Q: What happens if I need to delete data using Vald and Pydantic AI?

The deletevector tool permanently removes a vector from the index. Because this action is irreversible, you'll want to confirm your ID before executing it.

Q: Can my agent check the status of Vald using Pydantic AI?

Yes. Running getengineinfo retrieves detailed operational information and health status for the Vald engine, helping you confirm system readiness before deployment.

Write correct, production-grade agents that query dense vectors using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vald MCP to Pydantic AI

Create your Vinkius account to connect Vald to Pydantic AI 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 Vald with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search for Nearest Vectors with the MCP Server

The `search_vectors` tool finds nearest neighbors in your index. You pass it a query vector as a JSON array of floats, and Vald returns the closest matches from your knowledge base. This guarantees that when your agent pulls context, the data is highly relevant and immediately useful for generating correct outputs.

Updating Vectors with Pydantic AI

Use `update_vector` to refresh old entries. You need the existing ID and the new vector array. Vald handles the replacement, ensuring your knowledge base always reflects the latest source material. Need to add a whole new record? `insert_vector` is what you use; it requires both a unique ID and the JSON array of floats.

Validating Vald Engine Info

Before acting, check system health using `get_engine_info`. This tool retrieves operational information on the Vald engine so you know if it's ready to go. It's a crucial pre-flight check. For verification, `get_vector_details` lets your agent pull the raw vector data for any ID, making sure the source material is exactly what you expect.

Setup guide

Set up Vald 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": {
        "vald-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Vald 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 Vald. 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 Vald 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 Vald MCP in Pydantic AI

Use `search_vectors`. You send it a query vector (a JSON array of floats), and the MCP Server performs the nearest neighbor lookup. The agent gets accurate context instantly.

The `delete_vector` tool permanently removes a vector from the index. Because this action is irreversible, you'll want to confirm your ID before executing it.

Yes. Running `get_engine_info` retrieves detailed operational information and health status for the Vald engine, helping you confirm system readiness before deployment.

The primary data type is the dense vector—a JSON array of floats. You manage these vectors using specific unique identifiers for insertion, updates, or searches.

The MCP Server manages the storage of dense vector data. The agent interacts with this data through explicit tools like `get_vector_details` and `delete_vector`, ensuring controlled access.

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