How to Use the Certifier MCP in OpenAI Agents SDK

Q: How does my OpenAI Agents SDK agent issue a certificate with Certifier?

Your agent calls createcredential with the recipient's info and a template ID to make a draft. To finalize and send it, the agent then uses the issuecredential and sendcredential tools, all exposed by this MCP server.

Q: Can I update an issued certificate using Certifier and the OpenAI Agents SDK?

No, once a credential has been issued with issuecredential, it's locked. Your agent can only modify draft credentials using the updatecredential tool before they are finalized.

Q: What's the best way to find a template ID for Certifier in my OpenAI Agents SDK script?

Don't hard-code it. Have your agent call listcredentialtemplates to get all available templates. It can then parse the results to find the correct ID for the certificate it needs to create.

Q: How does the Certifier MCP Server connect to my agent?

You just pass the Vinkius URL to the MCPServerStreamableHttp constructor. The OpenAI Agents SDK automatically discovers all the tools from this MCP server, like createcredential, and adds them to your agent's context.

Build production agents that issue and manage digital credentials using the OpenAI Agents SDK. Zero config, full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Certifier MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Credential Issuing

Your agent can now manage the entire credential lifecycle. It starts by calling `create_credential` with a recipient's name, email, and a template ID. This generates a draft that can be reviewed or updated before it's final. Once the draft is approved, your agent uses `issue_credential`. This finalizes the certificate, assigns a public verification URL, and locks it from further changes. The whole process is visible in your OpenAI dashboard, so you have a full audit log.

Manage Templates and Designs

Stop hard-coding IDs. Your agent can dynamically find the right template for any situation. It uses `list_credential_templates` and `list_design_templates` to get a full catalog of what's available. Then, it can inspect a specific one with `get_credential_template` before passing its ID to the creation step. This makes your agent more flexible and less brittle. No more breaking changes when someone updates a template name on the Certifier side.

Find and Deliver Credentials with your MCP Server

This MCP Server gives your agent tools to find exactly what it's looking for. The `search_credentials` tool lets it find specific credentials by a recipient's name or email. You can also just get a complete list with `list_credentials`. After finding or creating a credential, the job's not done until it's delivered. Your agent calls `send_credential` to email the certificate directly to the recipient. The OpenAI Agents SDK guardrails can double-check the recipient's email before the send action is executed.

Setup guide

Set up Certifier 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 Certifier tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent calls `create_credential` with the recipient's info and a template ID to make a draft. To finalize and send it, the agent then uses the `issue_credential` and `send_credential` tools, all exposed by this MCP server.

No, once a credential has been issued with `issue_credential`, it's locked. Your agent can only modify draft credentials using the `update_credential` tool before they are finalized.

Don't hard-code it. Have your agent call `list_credential_templates` to get all available templates. It can then parse the results to find the correct ID for the certificate it needs to create.

You just pass the Vinkius URL to the `MCPServerStreamableHttp` constructor. The OpenAI Agents SDK automatically discovers all the tools from this MCP server, like `create_credential`, and adds them to your agent's context.

Certifier only processes the recipient's name and email to generate the credential. Vinkius secures the connection with a single token, and each MCP server runs in an ephemeral sandbox. Your data isn't stored.

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