How to Use the Modrinth MCP in Pydantic AI

Q: How do I perform a Modrinth search with Pydantic AI?

You invoke the searchprojects tool within your agent. Pydantic AI then validates the returned array against your defined model.

Q: Can I get dependency trees for Modrinth projects using Pydantic AI?

Yes, use getprojectdependencies. The server returns the tree, and Pydantic AI ensures the objects match your required format.

Q: What is the best way to connect the Modrinth MCP Server to Pydantic AI?

Use the MCPToolset class in your agent script. Point it at the server URL and your agent will auto-discover the available tools.

Use Pydantic AI with the Modrinth MCP Server to ensure every mod data point is type-validated and safe for your agent logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modrinth MCP to Pydantic AI

Create your Vinkius account to connect Modrinth 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 Modrinth with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly typed project lookups with Pydantic AI

The `get_project` tool provides raw data that your agent validates against Pydantic models. If the API structure changes, your agent crashes safely instead of processing bad data. This ensures your agent logic remains predictable. You never deal with silent corruption or missing fields.

Validated dependency traversal

Map your modpack requirements with `get_project_dependencies`. Because you are using Pydantic AI, each returned dependency is checked against your expected schema before the agent acts. This prevents runtime errors caused by unexpected API responses. You get high-quality data for your build scripts.

Reliable version and author identification

Use `list_versions` to find the exact file you need. Your agent verifies the version metadata against your constraints, ensuring you never pull the wrong loader version. It makes managing complex project histories simple. You keep your agent's knowledge base accurate and current.

Setup guide

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

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

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

You invoke the `search_projects` tool within your agent. Pydantic AI then validates the returned array against your defined model.

Yes, use `get_project_dependencies`. The server returns the tree, and Pydantic AI ensures the objects match your required format.

Since you define strict schemas, if the API returns an unexpected error object, Pydantic AI will trigger a validation error. This allows you to catch issues immediately.

Use the `MCPToolset` class in your agent script. Point it at the server URL and your agent will auto-discover the available tools.

Yes. The server only fetches public information from Modrinth. No user-specific data is stored or transmitted by the MCP layer.

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