How to Use the Range MCP in Pydantic AI

Q: Can Pydantic AI agents filter Range updates by user?

Your agent can call listupdates and apply filters for specific users or teams. The tool returns a structured list of check-ins that your agent can safely parse. This makes it easy to build automated weekly digests for individual developers.

Run type-safe async check-ins with Pydantic AI and ensure your Range updates never suffer from silent data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Range MCP to Pydantic AI

Create your Vinkius account to connect Range to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Range with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate team updates at the schema level

Using `create_update` runs with strict type-safety when invoked through Pydantic AI. If your agent tries to post a status update with missing fields or bad formats, the framework catches it before it hits the API. This strict validation prevents broken status updates from cluttering your team's feed. You get clean, predictable data in your workspace, and your Python code crashes immediately if something goes wrong.

Fetch structured objectives without hallucinations

Calling `list_objectives` and `get_objective` returns highly structured data that Pydantic AI validates against runtime models. The framework guarantees that every objective ID, team owner, and target date matches your expected types. Your agent can parse these targets to make decisions without risk of hallucinating non-existent fields. This makes your automated milestone tracking reliable enough for production deployment.

Query clean user directories via Pydantic AI

Running `list_users` and `get_user` allows your Pydantic AI agent to inspect your team structure safely. Every user profile, email, and department field is validated at runtime to ensure your agent never processes corrupt data. If a user profile is missing a critical field, the MCP Server connection handles the error gracefully. This keeps your automated routing scripts from failing silently when onboarding new employees.

Setup guide

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

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

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

You use the MCPToolset class with your Vinkius HTTP endpoint and pass it to your Agent's toolsets parameter. Pydantic AI connects to the external server and automatically builds the validation schemas for all 11 tools. Note that the older MCPServerHTTP class is deprecated and should not be used.

Pydantic AI will fail loudly and throw a validation error immediately. This prevents your agent from operating on bad data or hallucinating status details. It is the safest way to integrate team updates into your automated development pipelines.

Yes, Pydantic AI is completely model-agnostic. You can connect your local model or any commercial API to the Range MCP Server using the unified toolset interface. The validation layer works exactly the same regardless of which model you choose.

Your agent can call `list_updates` and apply filters for specific users or teams. The tool returns a structured list of check-ins that your agent can safely parse. This makes it easy to build automated weekly digests for individual developers.

All communication with the Range API goes through secure, isolated V8 sandboxes that do not persist your team updates or user lists. Vinkius manages the MCP tokens securely so your Pydantic AI scripts never expose raw credentials. Your organizational data remains private and ephemeral.

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