How to Use the Vectara MCP in Pydantic AI

Q: What is the best way to search data with Vectara and Pydantic AI?

Use performsemanticsearch. You pass the corpus keys and your query text. The MCP Server executes a semantic search across multiple corpora, giving you highly specific results.

Q: Can I check what data is available with Vectara and Pydantic AI?

You list all searchable datasets by calling listcorpora. To get the setup info on a particular dataset, run getcorpusdetails.

Q: Does the MCP Server support deleting documents?

Yes. You permanently remove data using deletecorpusdocument. The tool warns that this action is irreversible; you'll want to double-check before running it.

Q: How does the MCP Server manage chat history with Vectara and Pydantic AI?

You can see past interactions using listchatsessions. This lets your agent keep track of previous RAG sessions, which is critical for building reliable production systems.

Build validated, correct agents using your AI client: 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 Vectara MCP to Pydantic AI

Create your Vinkius account to connect Vectara 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 Vectara with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generating citations with RAG

When the agent needs an answer, it executes a RAG-powered chat completion via `execute_rag_chat`. This process returns summarized answers and provides explicit citations to the source material. It ensures correctness by grounding every response in your data sources. The output is validated against Pydantic models before you see it.

Deep searching across corpora

The agent uses `perform_semantic_search` to query one or more datasets simultaneously. You pass the corpus keys and the search text, and the MCP Server runs a deep semantic match. This mechanism lets your agent retrieve specific, context-aware data points that simple searches would miss.

Full visibility into datasets

You can check all indexed resources by running `list_corpora`. If you need details on how a dataset is configured, call `get_corpus_details`. It's also easy to audit what documents exist using `list_corpus_documents` for a specific corpus.

Setup guide

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

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

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

The MCP Server handles corpus documents, which are your source texts. Because the data is validated against Pydantic models at runtime, you get strong assurance about the integrity of what's being processed.

Use `perform_semantic_search`. You pass the corpus keys and your query text. The MCP Server executes a semantic search across multiple corpora, giving you highly specific results.

You list all searchable datasets by calling `list_corpora`. To get the setup info on a particular dataset, run `get_corpus_details`.

Yes. You permanently remove data using `delete_corpus_document`. The tool warns that this action is irreversible; you'll want to double-check before running it.

You can see past interactions using `list_chat_sessions`. This lets your agent keep track of previous RAG sessions, which is critical for building reliable production systems.

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