How to Use the Marchex MCP in Pydantic AI

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

Use the unified MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset instance to the Agent constructor in the toolsets list to enable automatic tool discovery.

Q: How does the toolset handle account-level queries?

The agent can call listaccounts or getaccountdetails to retrieve administrative metadata, parsing the results directly into type-safe Python dictionaries for your application logic.

Build type-safe Pydantic AI workflows that validate Marchex call records and campaign data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marchex MCP to Pydantic AI

Create your Vinkius account to connect Marchex 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 Marchex with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Call Auditing with Pydantic AI

The Marchex MCP Server relies on `get_call_details` and `search_calls` to pipe structured call records into your validation pipeline. Pydantic AI enforces strict schema validation on the returned JSON, preventing your agent from processing corrupt phone data. If the API returns unexpected values, the client raises a runtime validation error immediately. This loud-failure model ensures your production application never processes hallucinated call durations or broken caller IDs.

Validate Campaign Metrics via MCP Server

Executing `list_campaigns` and `get_campaign_details` within a Pydantic AI agent guarantees that your marketing metrics conform to strict Python types. The agent parses campaign budgets and tracking numbers directly into strongly-typed models. You initialize this by passing the unified `MCPToolset` HTTP URL directly to your agent's toolsets. The agent automatically discovers the schema, ensuring type-safe execution whether you use OpenAI, Anthropic, or local models.

Audit Telephony Setup via Pydantic AI

This MCP Server exposes `list_numbers` and `get_number_details` to let your agent verify your routing setup. The agent checks active tracking numbers and flags configuration mismatches before they impact your inbound sales lines. Because the framework is model-agnostic, you can swap your underlying LLM without rewriting your tool definitions. The agent will continue to query `get_call_analytics` with the exact same type guarantees.

Setup guide

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

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

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

Use the unified `MCPToolset` class with your Vinkius HTTP endpoint. Pass this toolset instance to the `Agent` constructor in the `toolsets` list to enable automatic tool discovery.

The framework raises a validation error at runtime. This prevents your agent from acting on malformed call data or corrupt campaign statistics, keeping your pipeline clean.

Yes, the toolkit supports both Streamable HTTP and SSE transports. Configure the `MCPToolset` with the appropriate Vinkius URL for your preferred transport method.

The agent can call `list_accounts` or `get_account_details` to retrieve administrative metadata, parsing the results directly into type-safe Python dictionaries for your application logic.

All telemetry, tracking numbers, and user lists are accessed through an ephemeral V8 sandbox. Vinkius handles credential storage, ensuring your API keys are never exposed to the LLM or stored in plain text.

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