How to Use the Glama MCP in OpenAI Agents SDK

Q: How do I link the Glama directory to my OpenAI Agents SDK project?

Initialize an MCPServerStreamableHttp instance pointing to the Glama endpoint. Pass this server object into your Agent constructor to enable auto-discovery of all available tools.

Q: Does Glama support model discovery for OpenAI Agents SDK agents?

Yes. Run glamagetgatewaymodels to audit the full list of compatible models. This ensures your agent selects the right gateway model before it attempts a chat.

Q: Can I filter server attributes inside my OpenAI Agents SDK workflow?

You can use glamagetmcpattributes to pull specific semantic metadata. This helps your agent decide which servers are relevant based on your current task requirements.

Q: Are private instances supported by this MCP Server?

Yes. Use glamagethostedinstances to fetch private servers linked to your account. This bypasses public directories for your internal agent needs.

Discover and route agents through the Glama gateway directly within your OpenAI Agents SDK production pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glama MCP to OpenAI Agents SDK

Create your Vinkius account to connect Glama 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 Glama with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and register Glama MCP tools

Use `glama_list_mcp_servers` to query the global directory and pull specific server configurations into your agent context. This lets your system find new capabilities on the fly. Once you find a target, call `glama_get_mcp_server_info` to grab the installation slug. Your agent then maps these tools into its local registry for immediate execution.

Execute model-specific gateway chats

Trigger `glama_run_gateway_chat` to route your prompt through the Glama proxy network using specific model IDs. It keeps your traffic flowing through a single endpoint. Call `glama_get_gateway_model_details` before you start to confirm your chosen model has the context window and parameters you need. This avoids runtime errors during agent execution.

Track telemetry in OpenAI Agents SDK

Monitor agent performance by invoking `glama_send_telemetry` after your agent completes an external tool call. It sends execution metrics back to the backend. Use this data to verify your agent's decision path. It provides a clear audit trail of which tools were used and how the gateway handled the request.

Setup guide

Set up Glama 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 Glama tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Glama 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="Glama Agent",
            instructions="You have access to Glama 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 Glama. 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 Glama 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 Glama MCP in OpenAI Agents SDK

Initialize an `MCPServerStreamableHttp` instance pointing to the Glama endpoint. Pass this server object into your Agent constructor to enable auto-discovery of all available tools.

Yes. Run `glama_get_gateway_models` to audit the full list of compatible models. This ensures your agent selects the right gateway model before it attempts a chat.

You can use `glama_get_mcp_attributes` to pull specific semantic metadata. This helps your agent decide which servers are relevant based on your current task requirements.

Yes. Use `glama_get_hosted_instances` to fetch private servers linked to your account. This bypasses public directories for your internal agent needs.

Your agent transmits raw prompt data and model configuration parameters to the Glama gateway. The server processes these via your unique token, ensuring your private keys never leave your controlled 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