How to Use the Capacities MCP in Pydantic AI

Q: Can I use Pydantic AI to update Capacities nodes?

You can combine getobject with your own update logic to modify existing records. Your agent validates the existing state before pushing changes back to the graph.

Strictly typed Capacities operations for your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capacities MCP to Pydantic AI

Create your Vinkius account to connect Capacities 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 Capacities with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI agents creating typed objects

Use `create_object` with Pydantic validation to ensure every field matches your graph schema. The agent fails early if the data doesn't fit your requirements. This eliminates silent errors where malformed data hits your workspace. You maintain the integrity of your graph with strict type checking.

Validate Capacities lookups in Pydantic AI

Use `lookup` to find nodes and validate the returned data against your Pydantic models. Your agent ensures the structure is correct before attempting to use the content. It catches missing properties or unexpected formats immediately. Your code logic stays robust because you know exactly what the response looks like.

Sync web content using Pydantic AI

Call `save_weblink` to capture URLs and let the server handle preview generation. Your agent validates the result object, ensuring the link is properly registered in your space. It keeps your web research organized. Every link is verified against your model before the agent proceeds to the next step.

Setup guide

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

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

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

You define the Pydantic models that validate the tool responses. This ensures that every object retrieved from your space meets your specific data requirements.

You can combine `get_object` with your own update logic to modify existing records. Your agent validates the existing state before pushing changes back to the graph.

If a tool call fails, Pydantic AI catches the exception during validation. You can then handle the error gracefully without crashing your agent process.

The server interacts with your space nodes, tags, and structure definitions. It only handles the data necessary to fulfill your specific tool requests.

We maintain no server-side storage of your notes. Your content is streamed directly between your local agent and your space, keeping your information private.

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