How to Use the R2R MCP in Pydantic AI

Q: How do I configure the R2R MCP Server in Pydantic AI?

Install the library using pip install "pydantic-ai-slimmcp". Use the MCPToolset class pointing to your server's HTTP endpoint, and pass it to your agent's toolsets list.

Q: Can my agent perform RAG queries using R2R and Pydantic AI?

Yes, your agent uses the ragquery tool to retrieve relevant context and generate verified answers directly from your ingested documents.

Q: How do I fetch a list of all indexed files?

The agent calls listdocuments to retrieve a list of all files in the system. This list is fully typed, making it easy to parse and display in your application's UI.

Run type-safe R2R vector searches and RAG queries with runtime validation in 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 R2R MCP to Pydantic AI

Create your Vinkius account to connect R2R 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 R2R with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Semantic Search with Pydantic AI

The `search` tool provides runtime validation for all your R2R operations. When your agent calls search, the returned vector data is validated against strict schemas, preventing silent failures or malformed outputs. You register the server by adding the HTTP toolset to your agent. Because Pydantic AI is model-agnostic, you get the same level of data integrity whether you use local models or external APIs.

Run Verified RAG Queries and Track Health

The `rag_query` tool retrieves synthesized answers grounded in your document store. This tool handles the retrieval and generation steps, returning a clean, validated response. To keep your production systems stable, the agent can call `get_health` to verify the database connection. This lets your application handle database downtime programmatically without crashing.

Inspect Validated Document Metadata and Collections

The `list_documents` tool and `get_document` inspect the files in your system. Every field in the returned document metadata is parsed and verified by Pydantic before your agent ever sees it. You can also call `list_collections` to manage logical groups of files. This allows your agent to construct precise, type-safe queries restricted to specific document groups.

Setup guide

Set up R2R 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": {
        "r2r-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to R2R tools.",
)

result = await agent.run("List recent R2R 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 R2R. 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 R2R 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 R2R MCP in Pydantic AI

Install the library using `pip install "pydantic-ai-slim[mcp]"`. Use the `MCPToolset` class pointing to your server's HTTP endpoint, and pass it to your agent's toolsets list.

Pydantic AI will raise a validation error at runtime. This prevents your agent from processing corrupt or incomplete document payloads returned by `search` or `get_document`.

Yes, your agent uses the `rag_query` tool to retrieve relevant context and generate verified answers directly from your ingested documents.

The agent calls `list_documents` to retrieve a list of all files in the system. This list is fully typed, making it easy to parse and display in your application's UI.

Your raw files and vector embeddings remain inside your secure R2R instance. The MCP Server only passes validated JSON payloads over local transport protocols, ensuring your sensitive text data is never stored or cached by third parties.

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