How to Use the Bland AI MCP in Pydantic AI

Q: How do I register the Bland AI MCP Server toolset in Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP URL. Pass this toolset into the toolsets argument when initializing your Agent instance.

Build type-safe voice workflows with Bland AI 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 Bland AI MCP to Pydantic AI

Create your Vinkius account to connect Bland AI 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 Bland AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate phone call parameters with Pydantic AI

`send_call` triggers a live outbound phone call using structured parameters that your agent validates at runtime. Pydantic AI ensures that phone numbers, pathway IDs, and custom variables match your exact schema before any API request is sent. You set this up by registering the Vinkius endpoint using `MCPToolset("http://...")` and passing it to your `Agent`. The framework handles the type checking, failing loudly if the server returns unexpected data formats.

Parse transcripts and call details with strict schemas

`get_transcript` fetches the text log of a completed call, while `get_call` retrieves the metadata and duration. The agent parses this raw data against your Pydantic models, preventing runtime errors caused by missing fields or unexpected null values. This MCP Server integration eliminates silent failures. If Bland AI updates its response structure, your application catches the mismatch immediately during the validation phase, keeping your production pipelines clean.

Audit voice pathways and agent rosters safely

`list_pathways` lists all active conversational trees, giving your agent the exact structure of your voice workflows. Your code can verify these pathways using `get_pathway` to ensure the call logic matches your expected business rules. By using this type-safe approach, you can programmatically manage your phone agents without worrying about malformed requests. The framework's model-agnostic nature means you can run these checks using any LLM provider.

Setup guide

Set up Bland AI 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": {
        "bland-ai-1-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the unified `MCPToolset` class pointing to your Vinkius HTTP URL. Pass this toolset into the `toolsets` argument when initializing your `Agent` instance.

The framework will raise a validation error at runtime. This prevents your agent from operating on corrupt call metadata or hallucinating transcript details.

Yes. Because the framework is model-agnostic, you can connect the server to local models, OpenAI, or Anthropic while maintaining strict type safety for all voice tools.

No, do not use the deprecated class. You should use the unified `MCPToolset` constructor, which supports both Streamable HTTP and SSE transports.

The server executes in a zero-trust, isolated V8 sandbox. Your API tokens and sensitive phone transcripts are processed on the fly and never stored on disk, ensuring complete data isolation.

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