How to Use the GlassFrog MCP in OpenAI Agents SDK

Q: How do I check if my connection to the server is active?

Run the verifyapiconnection tool. It performs a quick handshake with the GlassFrog API to confirm your token is valid. If it fails, your OpenAI Agents SDK agent catches the error before trying to run complex queries.

Run safe, multi-agent Holacracy workflows with OpenAI Agents SDK and our managed GlassFrog 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 GlassFrog MCP to OpenAI Agents SDK

Create your Vinkius account to connect GlassFrog to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate project creation with OpenAI Agents SDK

The `create_new_project` tool lets your OpenAI Agents SDK instance add tactical tasks directly to your GlassFrog circles. Your agent uses this tool to log updates immediately after team syncs. By configuring `cacheToolsList=True` in your OpenAI Agents SDK setup, the agent accesses the GlassFrog tool schema instantly. You track every single GlassFrog project creation event on your OpenAI developer dashboard to verify accuracy.

Audit circle roles without manual lookups

The `list_role_assignments` and `list_holacracy_roles` tools expose your exact GlassFrog structure to specialized agents. One agent pulls the current roster while another maps the roles. The OpenAI Agents SDK manages handoffs between these agents so you never leak raw GlassFrog data. You establish strict guardrails in the OpenAI Agents SDK constructor to prevent agents from modifying GlassFrog roles without human oversight.

Track circle metrics and policies on autopilot

The `list_circle_metrics` and `list_circle_policies` tools feed live GlassFrog governance rules and performance data straight to your LLM. Your agent reads these tools to analyze circle health. Because this GlassFrog MCP Server runs in a secure V8 sandbox, your OpenAI Agents SDK API keys stay protected. The OpenAI tracing dashboard logs every call to ensure your agents stay within their defined boundaries.

Setup guide

Set up GlassFrog MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all GlassFrog tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives GlassFrog tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GlassFrog tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="GlassFrog Agent",
            instructions="You have access to GlassFrog tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using pip install openai-agents and configure the MCPServerStreamableHttp class. Pass the Vinkius URL directly into your OpenAI Agents SDK constructor's mcp_servers list. Enable cacheToolsList=True to prevent unnecessary schema lookups on every run.

Yes, you enforce this by restricting agent tools in your OpenAI Agents SDK configuration. You can expose only read tools like list_circle_metrics while keeping create_new_project disabled for autonomous agents. This setup ensures your OpenAI Agents SDK won't modify your GlassFrog structure without explicit approval.

You define specialized agents for different administrative tasks in your OpenAI Agents SDK. For instance, one agent uses list_org_members to find a user, then hands off the context to a governance agent that calls list_role_assignments. The SDK manages this transition natively while keeping the GlassFrog connection open.

Run the verify_api_connection tool. It performs a quick handshake with the GlassFrog API to confirm your token is valid. If it fails, your OpenAI Agents SDK agent catches the error before trying to run complex queries.

Your organization's emails and circle structures are never stored or logged on Vinkius servers. The GlassFrog MCP Server executes inside an ephemeral V8 sandbox that destroys all session data immediately after processing. All API requests go directly to GlassFrog via encrypted HTTPS connections.

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