How to Use the Namely MCP in Pydantic AI

Q: How does Pydantic AI connect to this MCP server?

It's simple. You'll install pydantic-ai-slimmcp and then create an MCPToolset instance using your Vinkius server URL. Add that toolset to your agent's toolsets list.

Q: Is it hard to use the Namely MCP Server with Pydantic AI?

No, Pydantic AI makes it easy. The MCPToolset handles all the discovery and HTTP communication. As long as your agent knows about the toolset, it can start using the Namely tools.

Q: How does Pydantic AI work with custom Namely fields?

Your agent can call the listfields tool to get the schema of your custom fields. You can then dynamically create or update your Pydantic models to include these fields, ensuring even your custom data is type-checked at runtime.

Bring type-safe access to your Namely HR data into any Python agent with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Namely MCP to Pydantic AI

Create your Vinkius account to connect Namely 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 Namely with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce Correctness on HR Data

This MCP server lets your agent call tools like `get_profile` and `list_profiles`, but with a critical difference: Pydantic AI validates every response. If the Namely API returns a profile with a missing field or wrong data type, your code will raise a `ValidationError` instantly. This means no more silent data corruption bugs. You can trust that the data from `get_team` or `list_teams` perfectly matches the Pydantic model you've defined in your Python code. It's about building reliable, predictable HR automations.

Build Model-Agnostic HR Agents

Because Pydantic AI isn't tied to one LLM provider, you can use these Namely tools with OpenAI, Anthropic, Gemini, or even a local model. The tools, like `list_announcements` and `list_events`, will work the same way everywhere. This frees you to choose the best model for the job, whether you're summarizing company news from `list_announcements` or building a simple chatbot that can look up a colleague's work anniversary from `list_events`.

Query Your Namely MCP Server with Confidence

Get structured, validated access to your company's job and reporting data. The `list_jobs` tool returns a list of job titles that conforms to a strict schema, so your agent won't choke on unexpected formatting. You can also use `list_reports` to pull HR reports and `list_fields` to see your custom data schema. With Pydantic AI, you're not just calling an API; you're interacting with a guaranteed data contract for your entire Namely instance.

Setup guide

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

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

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

It's simple. You'll install `pydantic-ai-slim[mcp]` and then create an `MCPToolset` instance using your Vinkius server URL. Add that toolset to your agent's `toolsets` list.

Build a data integrity monitor. Have an agent periodically use this MCP server to run `list_profiles` and `list_teams` and validate the responses against your master Pydantic models. It can automatically flag any records in Namely that have drifted from the expected schema.

No, Pydantic AI makes it easy. The `MCPToolset` handles all the discovery and HTTP communication. As long as your agent knows about the toolset, it can start using the Namely tools.

Your agent can call the `list_fields` tool to get the schema of your custom fields. You can then dynamically create or update your Pydantic models to include these fields, ensuring even your custom data is type-checked at runtime.

Data security starts with data integrity. This server ensures that only data matching a strict schema—like employee profiles and job info—is ever passed to your agent. This prevents unexpected data leakage, and all traffic runs through Vinkius's isolated, encrypted environment.

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