How to Use the Mention MCP in Pydantic AI

Q: Can Pydantic AI handle schema mismatches when calling Mention tools?

Yes, if a tool like getalertdetails returns unexpected data, Pydantic AI raises a clear validation error. This prevents your agent from making decisions based on corrupted or misaligned JSON payloads.

Q: Does Pydantic AI support model-agnostic execution with Mention?

Absolutely. You can use Pydantic AI to run searchmentionsbykeyword using OpenAI, Anthropic, Gemini, or even a local model. The framework handles the MCP validation layer independently of the LLM provider you choose.

Q: How do I safely delete alerts using Pydantic AI?

Your agent can run removemonitoringalert by passing the target alert ID. The framework validates that the ID format is correct before executing the tool, preventing accidental deletions from malformed inputs.

Q: How does the Pydantic AI protect my Mention profile data and credentials?

The framework processes your account profile data from getmyprofile entirely in-memory. Your Vinkius endpoint token is handled via secure HTTP headers, and no brand data or profile information is ever cached or stored on external validation servers.

Build rock-solid brand monitoring agents with Pydantic AI to validate every Mention alert and metric 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 Mention MCP to Pydantic AI

Create your Vinkius account to connect Mention 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 Mention with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Mention Metrics with Strict Pydantic AI Schemas

Your agent executes `get_alert_statistics` to fetch reach metrics and volume statistics. Pydantic AI enforces strict runtime validation on the incoming JSON, ensuring that numerical fields like reach and share of voice match your expected type definitions. If the Mention API schema changes or returns unexpected null values, the framework raises a validation error immediately. This strict behavior prevents your application from processing malformed data or propagating silent errors downstream.

Type-Safe Reputation Tracking and Alert Management

The agent calls `list_monitoring_alerts` to retrieve your active tracking configurations. Pydantic AI maps the returned alert data directly to type-safe Python models, making it impossible for your agent to hallucinate alert IDs or parameters. When creating new tracking parameters, the agent runs `create_monitoring_alert` with fully validated inputs. The framework verifies the payload structure before sending it to the MCP Server, keeping your configuration clean.

Parse Brand Mentions Without Hallucinated Fields

Your agent runs `list_recent_mentions` to ingest the latest brand discussions from social media and blogs. Pydantic AI validates the structure of every single finding, ensuring fields like timestamps, source URLs, and text content are correctly typed. When your agent processes this data using `get_mention_content`, you can be certain the output matches your internal data models. This type safety is critical when piping brand mentions directly into production databases or notification systems.

Setup guide

Set up Mention 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": {
        "mention-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your Agent's toolsets parameter, and the framework will automatically discover all 12 brand monitoring tools.

Yes, if a tool like get_alert_details returns unexpected data, Pydantic AI raises a clear validation error. This prevents your agent from making decisions based on corrupted or misaligned JSON payloads.

Absolutely. You can use Pydantic AI to run search_mentions_by_keyword using OpenAI, Anthropic, Gemini, or even a local model. The framework handles the MCP validation layer independently of the LLM provider you choose.

Your agent can run remove_monitoring_alert by passing the target alert ID. The framework validates that the ID format is correct before executing the tool, preventing accidental deletions from malformed inputs.

The framework processes your account profile data from get_my_profile entirely in-memory. Your Vinkius endpoint token is handled via secure HTTP headers, and no brand data or profile information is ever cached or stored on external validation servers.

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