How to Use the BrandMentions MCP in Pydantic AI

Q: How do I register the MCP server for BrandMentions in Pydantic AI?

Use the unified MCPToolset class initialized with your Vinkius HTTP endpoint, and pass that directly in your agent's toolsets list. This replaces the deprecated HTTP server classes.

Run type-safe social listening with Pydantic AI to guarantee your brand tracking data matches your schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BrandMentions MCP to Pydantic AI

Create your Vinkius account to connect BrandMentions 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 BrandMentions with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect BrandMentions to Pydantic AI securely

This MCP Server brings type-safe brand tracking and social listening tools directly to your validation pipelines. When your agent calls `get_project_mentions` or `list_projects`, every field is checked against Pydantic models at runtime, preventing malformed data from breaking your application. This model-agnostic approach means you can swap LLM providers behind the scenes without worrying about how they parse raw JSON. If the API structure changes, your system fails loudly and immediately, rather than silently passing bad tracking data to your database.

Validate live social listening data at runtime

Running ad-hoc searches shouldn't introduce unpredictable payloads to your codebase. Connecting an MCP server to your workflow lets you use `post_search` to kick off a search and `get_mentions` to ingest the results, ensuring that every social post, author name, and reach metric matches your exact schema before processing. You can also retrieve partial results using `get_processed_mentions` while a search is still running. Because the data is validated immediately, your downstream sentiment analysis steps won't choke on unexpected null fields or weird formatting.

Audit campaigns and influencers with strict schemas

Managing campaign settings and influencer lists requires absolute precision. Using this MCP server, your agent can query `get_influencers` to identify key creators or set up tracking using `add_project` and `delete_project` with complete confidence that the parameters match the expected types. Keep an eye on your operational limits by checking `get_remaining_credits`. The type-safe responses make it simple to write automated checks that alert your team if credit usage spikes unexpectedly, keeping your infrastructure predictable.

Setup guide

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

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

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

Use the unified `MCPToolset` class initialized with your Vinkius HTTP endpoint, and pass that directly in your agent's `toolsets` list. This replaces the deprecated HTTP server classes.

The framework will raise a validation error instantly. This prevents your agent from processing broken or hallucinated social listening fields, protecting your downstream databases.

Yes. The framework fully supports async operations, letting your agent trigger searches with `post_search` and monitor progress with `get_processed_mentions` without blocking other tasks.

Yes. Pydantic AI is completely model-agnostic, meaning you can run this server alongside local models or commercial APIs while maintaining strict schema validation.

Your brand keywords, project configurations, and fetched mentions are routed through secure, short-lived V8 isolates. No data is stored on Vinkius infrastructure, and all communication uses encrypted transport protocols to prevent exposure.

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