How to Use the Beeceptor MCP in OpenAI Agents SDK

Q: Will my agent know if a rule update fails?

If updaterulepartial fails due to bad JSON formatting, the server returns the raw API error. Your agent catches this response immediately, allowing it to correct the payload and retry the call.

Build production-grade agents that control Beeceptor mock APIs using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beeceptor MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control mock routing rules using OpenAI Agents SDK

`create_rule` lets your agent build HTTP mock endpoints on the fly during live test runs. This MCP Server exposes direct control over your Beeceptor mock server, letting your code verify how your system handles API failures or custom headers. If a test path changes, the agent can call `update_rule_full` or `reorder_rules` to adjust routing priority instantly. You don't have to manually click through a web UI to update mock responses while running CI pipelines.

Inspect live HTTP traffic inside your agent loop

`list_requests` pulls real-time HTTP payloads and headers directly into your agent's context. This tool gives your runner immediate eyes on what your webhook sender actually dispatched, making debugging asynchronous callbacks incredibly fast. Your agent can isolate specific failures with `get_request` or wipe the slate clean using `delete_requests` between test suites. It keeps your test environments clean and prevents old payloads from leaking into new runs.

Manage secure mTLS certificates programmatically

`add_certificate` uploads client certificates directly to your mock endpoints. This capability allows your automated test agents running this MCP Server to establish secure, mutual TLS connections with upstream services without manual key provisioning. When a test finishes or a certificate expires, the agent invokes `delete_certificate` to revoke access. Security stays tight because credentials exist only for the duration of the test run.

Setup guide

Set up Beeceptor 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 Beeceptor tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK using pip, then instantiate MCPServerStreamableHttp with your Vinkius endpoint URL. Pass this instance to your Agent constructor inside an async context manager to auto-discover all 29 tools.

Yes, you can limit tool access by defining strict system instructions or using specialized agent handoffs. This prevents a testing agent from accidentally calling destructive tools like delete_all_rules when it only needs to read requests.

Set cacheToolsList=True in your connection parameters. This stops the agent from fetching the tool schema on every single turn, making your mock API modifications much faster.

If update_rule_partial fails due to bad JSON formatting, the server returns the raw API error. Your agent catches this response immediately, allowing it to correct the payload and retry the call.

All mock rules, HTTP request headers, and payloads remain isolated within your Vinkius V8 sandbox. No raw traffic or sensitive API payloads are stored on the host platform, ensuring your test data stays private.

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