How to Use the VectorShift (AI Workflow & RAG Automation) MCP in Pydantic AI

Q: How do I process a multi-step workflow using VectorShift (AI Workflow & RAG Automation) with the Pydantic AI?

Start by defining your sequence using createpipeline. You then execute it via runpipeline, providing all necessary inputs for the entire flow. The MCP Server ensures that every step validates its output before proceeding.

Q: Where can I find information on how to search my private documents using VectorShift (AI Workflow & RAG Automation) with the Pydantic AI?

Use queryknowledgebase. This tool performs semantic search, looking through all indexed data to answer your query. You must first ensure the files are loaded into a knowledge base using indexknowledgebase.

Q: If I need to change my chatbot's context or source documents using VectorShift (AI Workflow & RAG Automation) with the Pydantic AI, what should I do?

You can update the knowledge base by calling indexknowledgebase with new content. If you want to remove old data entirely, use deleteknowledgebasedocuments referencing specific IDs.

Type-safe AI workflows for production agents using Pydantic AI and VectorShift (AI Workflow & RAG Automation).

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VectorShift (AI Workflow & RAG Automation) MCP to Pydantic AI

Create your Vinkius account to connect VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Chatbots

You can set up a chatbot with `create_chatbot` and then manage its inputs by calling `upload_chatbot_files`. This ensures the agent has specific, timely context for conversation. The core interaction happens when you call `run_chatbot`, sending messages that are processed through the established chat logic. Remember to use `list_chatbots` if you need a list of existing services.

Manage Knowledge Bases

The `query_knowledge_base` tool lets your agent search indexed data using semantic retrieval, giving highly accurate answers. You maintain the source material by calling `index_knowledge_base` with new files or URLs. Need to clean up? Use `delete_knowledge_base` or narrow down removals with `delete_knowledge_base_documents`.

Execute Pipelines

Pipelines handle multi-step tasks, starting with `create_pipeline`. These pipelines are essential for complex operations that require multiple tools to talk to each other in order. You run the sequence using `run_pipeline`, passing all required inputs. If you need to modify data between steps, use `run_transformation` after defining it via `create_transformation`.

Setup guide

Set up VectorShift (AI Workflow & RAG Automation) 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": {
        "vectorshift-ai-workflow-rag-automation-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to VectorShift (AI Workflow & RAG Automation) tools.",
)

result = await agent.run("List recent VectorShift (AI Workflow & RAG Automation) 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 VectorShift. 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 VectorShift (AI Workflow & RAG Automation) 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 VectorShift (AI Workflow & RAG Automation) MCP in Pydantic AI

Start by defining your sequence using `create_pipeline`. You then execute it via `run_pipeline`, providing all necessary inputs for the entire flow. The MCP Server ensures that every step validates its output before proceeding.

Use `query_knowledge_base`. This tool performs semantic search, looking through all indexed data to answer your query. You must first ensure the files are loaded into a knowledge base using `index_knowledge_base`.

You can update the knowledge base by calling `index_knowledge_base` with new content. If you want to remove old data entirely, use `delete_knowledge_base_documents` referencing specific IDs.

You have fine-grained controls. To manage running pipelines, use `pause_pipeline` or `terminate_pipeline`. You can also pause individual chatbot sessions using `pause_chatbot`.

This server processes and stores raw document files, URLs, and textual content when they are indexed into a knowledge base. The critical data type is source text.

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