How to Use the Bandcamp MCP in Pydantic AI

Q: How do I add Bandcamp to Pydantic AI?

Use the MCPToolset class with your Vinkius HTTP endpoint URL. Pass the resulting toolset directly into your Agent constructor. Ensure you are using the slim package with the MCP extra.

Q: Will Pydantic AI catch bad Bandcamp URLs?

If you pass a broken link to getpagedata, the extraction fails and the framework throws a clear error. You handle the exception in your code rather than dealing with hallucinated metadata.

Q: Can I search Bandcamp using Pydantic AI?

Yes. The agent calls the search tool with a text string. It receives a strictly typed array of artists, albums, tracks, labels, or fan profiles in return.

Q: What genres are supported for new releases?

The agent must call gettags to fetch the current list of valid genres. It can then pass any of those tags into getnewreleases to fetch the latest drops.

Type-safe Bandcamp music extraction 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 Bandcamp MCP to Pydantic AI

Create your Vinkius account to connect Bandcamp 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 Bandcamp with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict validation for music data

Independent music APIs are notoriously messy. You need absolute certainty that the data coming back matches your schema. Connect this MCP server via `MCPToolset` and Pydantic AI forces every single response through strict runtime validation. If `get_page_data` returns a missing price field or a malformed tracklist, the framework fails loudly. You catch the validation error immediately instead of letting silent corruption poison your database. Your agent only acts on perfectly typed JSON.

A model-agnostic Bandcamp MCP Server

Lock-in is a massive risk for production systems. Because this integration relies on the open standard, you can swap between proprietary models or local alternatives without rewriting your tool logic. The MCP Server runs externally while your agent handles the execution. Start by having your agent run `search` to locate specific labels. It then takes those URLs and feeds them into `get_new_releases` or `get_recommended`. Every step of the chain is heavily typed and verified before the LLM even sees the payload.

Track editorial and sales metrics

Building a reliable scouting pipeline requires accurate metadata. Your agent triggers `get_featured` to pull front-page stories, then verifies those artists against the charts using `get_best_selling`. The system never guesses at available genres. It executes `get_tags` first to pull the definitive list. Then it passes those exact strings into `discover_music`, guaranteeing that the subsequent API calls actually work.

Setup guide

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

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

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

Use the `MCPToolset` class with your Vinkius HTTP endpoint URL. Pass the resulting toolset directly into your Agent constructor. Ensure you are using the slim package with the MCP extra.

If you pass a broken link to `get_page_data`, the extraction fails and the framework throws a clear error. You handle the exception in your code rather than dealing with hallucinated metadata.

Yes. The agent calls the `search` tool with a text string. It receives a strictly typed array of artists, albums, tracks, labels, or fan profiles in return.

The agent must call `get_tags` to fetch the current list of valid genres. It can then pass any of those tags into `get_new_releases` to fetch the latest drops.

Vinkius executes every tool call in an isolated, ephemeral V8 environment. The server extracts public tracklists, release dates, and editorial picks. Once the request finishes, the sandbox is destroyed, leaving zero logs of your specific scouting targets.

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