How to Use the Mela MCP in Pydantic AI

Q: How do I set up Pydantic AI with the Mela MCP Server?

Install pydantic-ai-slimmcp and initialize MCPToolset with your HTTP endpoint. Pass this toolset to your agent to immediately expose all 12 project management tools.

Q: Does Pydantic AI support both HTTP and SSE transports for Mela?

Yes, the unified MCPToolset class handles both streamable HTTP and SSE connections. Make sure your external server is running, and pass the URL directly to the toolset.

Run type-safe project management workflows with Mela and Pydantic AI validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mela MCP to Pydantic AI

Create your Vinkius account to connect Mela 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 Mela with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Mela MCP Server logs at runtime

This integration routes `log_work_hours` and `log_materials` through Pydantic AI's strict validation engine. Every number, text field, and ID returned by the Mela server is validated against Pydantic AI models before your agent runs. You catch malformed API responses before they break your application. If a tool returns a string where a number was expected, the Pydantic AI framework fails loudly. It prevents silent data corruption in your Mela project logs. Your agent always works with clean, verified data.

Query site activities without silent errors

The MCP Server exposes `get_activity` and `get_accounting_data` to feed structured data into your Pydantic AI models. You define the exact schema your application expects, and the framework enforces it. It guarantees your financial reports never parse raw, unvalidated JSON. This is critical when pulling Mela cost metrics. If the server schema changes, your Pydantic AI agent stops immediately instead of writing bad calculations to your database. It gives you production-grade reliability for on-site accounting.

Send structured updates to project feeds

Your agent uses `post_message` and `list_users` to coordinate teams using strongly-typed Pydantic AI payload models. The framework ensures every message body and user ID matches your internal database schemas before sending to Mela. It prevents broken links and empty messages on your project board. This framework is model-agnostic, meaning you can run these validated Mela tools with OpenAI, Anthropic, or local models. Validation happens at the Python level, keeping your MCP messaging system bulletproof regardless of the LLM you use.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and initialize `MCPToolset` with your HTTP endpoint. Pass this toolset to your agent to immediately expose all 12 project management tools.

The framework raises a validation error immediately at runtime. This prevents your agent from processing corrupt data or making decisions based on bad inputs.

Yes, the unified `MCPToolset` class handles both streamable HTTP and SSE connections. Make sure your external server is running, and pass the URL directly to the toolset.

Yes, the framework is model-agnostic. You can connect local models like Llama or Mistral and still get strict type validation for tools like `list_activities`.

It utilizes our zero-trust V8 sandbox to isolate all user queries. The framework validates inputs before they reach the API, ensuring `list_users` only runs with correct parameters. Your employee records are never exposed to insecure environments.

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