How to Use the GlassFrog MCP in Pydantic AI

Q: How do I connect the GlassFrog MCP server to a Pydantic AI agent?

Install the package with pip install "pydantic-ai-slimmcp" and initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset into the Pydantic AI Agent's toolsets parameter. The agent automatically discovers all 12 GlassFrog tools and validates their inputs.

Q: How do I verify that my API key is configured correctly?

You run the verifyapiconnection tool as a pre-flight check in your Pydantic AI initialization. It returns a boolean status indicating whether the server can successfully authenticate with GlassFrog. If it returns false, you can halt your application before running any agent loops.

Build type-safe Holacracy integrations using Pydantic AI to validate GlassFrog data structures 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 GlassFrog MCP to Pydantic AI

Create your Vinkius account to connect GlassFrog 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 GlassFrog with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate GlassFrog records at runtime with Pydantic AI

The `get_circle_summary` tool retrieves structured GlassFrog governance data that Pydantic AI validates against strict schemas. If the API returns unexpected fields, your application fails loudly instead of passing corrupted data. You register the GlassFrog MCP server using the MCPToolset class and pass it directly to your Pydantic AI Agent. This type-safe pipeline guarantees that your Python code receives exactly the structure it expects.

Query members and roles with strict type safety

The `find_member_by_email` and `list_holacracy_roles` tools let you search your GlassFrog organization without risking silent type coercion errors in Pydantic AI. The MCP Server outputs clean JSON that maps directly to your local models. Because Pydantic AI is model-agnostic, you can swap your underlying LLM while keeping these strict validation layers. Your Pydantic AI agent will always receive strongly typed GlassFrog member records.

Safely execute tactical project updates

The `create_new_project` tool requires specific parameters that Pydantic AI validates before the request ever leaves your server. This prevents your agent from sending malformed payloads to GlassFrog. By running this GlassFrog MCP Server on Vinkius, you eliminate the need to run local Node or Python processes. The external server handles the API connection while your local Pydantic AI agent focuses on strict validation.

Setup guide

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

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

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

Install the package with pip install "pydantic-ai-slim[mcp]" and initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset into the Pydantic AI Agent's toolsets parameter. The agent automatically discovers all 12 GlassFrog tools and validates their inputs.

The Pydantic AI framework immediately raises a validation error and halts execution. This prevents your agent from processing corrupted GlassFrog circle summaries or bad role assignments. It ensures your application fails safely and loudly rather than continuing with bad data.

No, you should use the unified MCPToolset class instead of MCPServerHTTP for your GlassFrog integration. The MCPServerHTTP class is deprecated in recent versions of Pydantic AI. The new toolset class simplifies connection management for both Streamable HTTP and SSE transports.

You run the verify_api_connection tool as a pre-flight check in your Pydantic AI initialization. It returns a boolean status indicating whether the server can successfully authenticate with GlassFrog. If it returns false, you can halt your application before running any agent loops.

All GlassFrog policy and assignment data is processed inside secure V8 isolates that do not persist state. Your authorization tokens are handled by Vinkius's zero-trust gateway and never written to logs or disk. Your data remains strictly between your Pydantic AI runtime and the GlassFrog API.

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