How to Use the FreeClimb MCP in Pydantic AI

Q: How do I connect FreeClimb to Pydantic AI?

Install pydantic-ai-slimmcp. Use the unified MCPToolset class pointing to your MCP server endpoint. Pass this toolset array to your Agent constructor.

Q: Does Pydantic AI validate FreeClimb API responses?

Yes. Every time the agent calls getcalldetails or getsmsdetails, the framework checks the response against strict runtime models.

Q: Which transport method should I use for this MCP server?

Use Streamable HTTP or SSE transports. The older MCPServerHTTP class is deprecated, so stick to the unified MCPToolset approach.

Type-safe FreeClimb integration for 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 FreeClimb MCP to Pydantic AI

Create your Vinkius account to connect FreeClimb 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 FreeClimb with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validated messaging for Pydantic AI

Silent failures ruin communication workflows. When your agent uses `send_sms`, Pydantic AI validates the exact payload structure before hitting the FreeClimb API. If the model hallucinates a parameter, the agent fails loudly. You track message history by invoking `list_sms_messages`. Every response from `get_sms_details` maps directly to a strict Pydantic model. You never deal with missing fields or corrupt data.

Type-checked voice interactions

Dialing out requires precise routing instructions. The agent triggers `make_call` with validated destination numbers. It checks `list_conferences` to monitor active bridges without guessing the schema. Call metadata is complex. When the agent pulls `list_calls` or `get_call_details`, the framework guarantees the response matches your expectations. You spend zero time writing defensive parsing logic.

Account management via this MCP Server

Provisioning numbers programmatically is risky if the agent gets confused. This MCP Server exposes `list_buyable_numbers` so the agent can search inventory. It checks `list_my_numbers` to avoid buying duplicates. The agent monitors billing limits by calling `get_account_status`. It also audits your routing configurations using `list_applications` and `get_application_details`. Every single API call is strictly typed.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Use the unified `MCPToolset` class pointing to your MCP server endpoint. Pass this toolset array to your Agent constructor.

Yes. Every time the agent calls `get_call_details` or `get_sms_details`, the framework checks the response against strict runtime models.

The framework is model-agnostic. You can use Anthropic, OpenAI, or local models to drive the `make_call` and `send_sms` tools.

Use Streamable HTTP or SSE transports. The older `MCPServerHTTP` class is deprecated, so stick to the unified `MCPToolset` approach.

The tools access sensitive call metadata and billing status. Vinkius hosts the server in a managed, zero-trust environment. You authenticate with a single token, and no persistent state remains after the agent finishes its task.

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