How to Use the Bear MCP in Pydantic AI

Q: How do I configure the Bear MCP Server with Pydantic AI?

Use the MCPToolset class pointing to the Vinkius hosted HTTP endpoint. Pass this toolset directly into your Agent's toolsets parameter to instantly expose all ten tools.

Q: Can Pydantic AI agents search my Bear tags safely?

Yes. The agent uses opentag and listtags to query your taxonomy. The returned data is validated against strict Pydantic schemas before your agent even reads it.

Build rock-solid Python agents that edit and search Bear notes with strict Pydantic AI runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bear MCP to Pydantic AI

Create your Vinkius account to connect Bear 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 Bear with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Markdown Generation with Pydantic AI

This MCP Server exposes the `create_note` and `add_text` tools to let your agent write structured markdown notes. Every single response and parameter is validated against Pydantic models before execution, preventing malformed notes from breaking your database. If the model attempts to pass an invalid parameter or corrupted text, the framework fails loudly with a validation error. This keeps your personal wiki clean and free from half-baked formatting or silent errors.

Strict Taxonomy Control and Renaming

The `list_tags` and `rename_tag` tools let your agent manage complex nested tag hierarchies. The agent queries your global tag taxonomy, ensuring that any rename operations conform exactly to your defined string formats. You get complete control over your tags without worrying about LLM hallucinations. The schema validation ensures that only valid, clean tag strings are applied to your notes via the MCP Server.

Validated Note Search and Archiving

The `search_notes` and `archive_note` tools allow your agent to scan your knowledge base and archive completed tasks. The agent parses search results into strongly typed Python objects, making it easy to filter by specific criteria. Because the data is validated at runtime, you can safely automate workflows like archiving notes tagged with specific metadata. There is no risk of the agent misinterpreting the note payload and archiving the wrong file.

Setup guide

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

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

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

Use the `MCPToolset` class pointing to the Vinkius hosted HTTP endpoint. Pass this toolset directly into your Agent's `toolsets` parameter to instantly expose all ten tools.

The framework will raise a validation error immediately. This prevents your agent from processing corrupted markdown or hallucinated fields, keeping your pipeline clean.

Yes. The agent uses `open_tag` and `list_tags` to query your taxonomy. The returned data is validated against strict Pydantic schemas before your agent even reads it.

Yes. The Vinkius hosted server supports both Streamable HTTP and SSE transports, allowing you to choose the best connection method for your production environment.

Your markdown chunks, tags, and search queries are processed inside an ephemeral, zero-trust sandbox. No personal note content is ever cached or written to disk on our infrastructure.

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