How to Use the Keywords AI MCP in Pydantic AI

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

You instantiate MCPToolset with the server's HTTP URL and pass it to your agent's constructor. Pydantic AI automatically discovers tools like listmodels and getanalytics and validates their inputs.

Q: Can Pydantic AI validate the cost data returned by Keywords AI?

Yes, tools like getusagestats and getcredits return strictly typed data. Pydantic AI validates these numbers at runtime, ensuring your budget calculations are always accurate.

Q: What happens if Keywords AI returns an unexpected model schema?

If listmodels returns data that violates the expected schema, Pydantic AI raises a validation error immediately. This prevents your agent from attempting to route traffic to invalid or malformed model endpoints.

Q: Can I filter request logs by model safely?

Yes, using listrequestsbymodel returns a structured list of logs filtered by your target model. The agent parses this list into typed Python objects for safe evaluation.

Run type-safe LLM monitoring inside Pydantic AI with runtime validation using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keywords AI MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe LLM log inspection in Pydantic AI

`get_request` returns structured, type-safe LLM log data that Pydantic AI validates at runtime before your agent processes it. This guarantees that your agent never acts on corrupted payload data or malformed API responses. Your agent also uses `list_requests` to fetch historical logs. Because every field matches your Pydantic schemas, you eliminate runtime crashes caused by unexpected API schema changes from external providers.

Validate spend and credits using this MCP Server

`get_credits` provides your Pydantic AI agent with a strictly validated float representing your remaining balance. The agent uses this to enforce hard financial budgets, halting execution if the returned credit value falls below your safety threshold. By calling `get_analytics`, your agent retrieves structured cost and latency metrics. This allows you to build self-correcting loops where the agent shifts to cheaper models when budget limits are breached.

Monitor team users and active alerts securely

`list_alerts` delivers a validated list of system errors and latency spikes directly to your Pydantic AI agent. This allows your agent to raise native Python exceptions or trigger alerts if any upstream provider begins failing. You can also query `list_users` to audit team access. The returned list of team members is parsed into strict Python models, making it easy to enforce access control rules inside your application.

Setup guide

Set up Keywords 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": {
        "keywords-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You instantiate `MCPToolset` with the server's HTTP URL and pass it to your agent's constructor. Pydantic AI automatically discovers tools like `list_models` and `get_analytics` and validates their inputs.

Yes, tools like `get_usage_stats` and `get_credits` return strictly typed data. Pydantic AI validates these numbers at runtime, ensuring your budget calculations are always accurate.

If `list_models` returns data that violates the expected schema, Pydantic AI raises a validation error immediately. This prevents your agent from attempting to route traffic to invalid or malformed model endpoints.

Yes, using `list_requests_by_model` returns a structured list of logs filtered by your target model. The agent parses this list into typed Python objects for safe evaluation.

The server runs in a secure, ephemeral V8 isolate sandbox. Your gateway API keys and LLM usage statistics are processed in-memory and never written to disk, ensuring your Pydantic AI application remains compliant.

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