How to Use the Assertible MCP in AutoGen

Q: How do AutoGen agents collaborate on Assertible test runs?

One agent triggers a run using runservicetests while another analyzes the results through the AutoGen MCP adapter. They discuss the failures to determine if a deployment should be blocked.

Q: Can an AutoGen agent update my Assertible API specs?

Yes, an agent can call syncspecification with your latest OpenAPI file. This ensures all agents in the conversation are testing against the correct API endpoints.

Q: How do AutoGen agents handle failed Assertible deployments?

When createdeployment returns a failure, the monitoring agent alerts the coordinator agent. They then run targeted diagnostics to find the broken endpoint.

Q: Is authentication required to validate JSON structures?

No, validatejson does not require any tokens. Your agents can use it freely to check payload formats during their debugging conversations.

Let AutoGen agents debate deployment safety and execute Assertible API tests before promoting builds.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Assertible MCP to AutoGen

Create your Vinkius account to connect Assertible to AutoGen 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 Assertible with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents coordinate deployment testing

Managing deployments with `create_deployment` allows your agents to coordinate and verify releases autonomously. You can set up a multi-agent workflow where a DevOps agent triggers a build using the Assertible MCP Server. If issues arise, the agents use `run_service_tests` to verify the entire system. They debate the results in real-time, agreeing to halt the pipeline if critical assertions fail.

Resolve schema conflicts through agent debate

Updating API specs with `sync_specification` ensures your entire multi-agent team tests against current definitions. When your API definition changes, a developer agent can update Assertible instantly. A separate validation agent then runs `validate_json` on sample payloads to check for breaking changes within the MCP framework. These agents discuss any validation errors they find, working together to fix the payloads before merging.

Run targeted test execution during outages

Running isolated checks with `run_specific_test` lets your agents pinpoint broken routes during an active outage. One agent checks endpoint health using `get_service_status_badge`, while another runs targeted diagnostics on suspected routes. By isolating the failing tests, the agents quickly locate the broken service. This targeted approach prevents long feedback loops and helps your team resolve downtime faster.

Setup guide

Set up Assertible MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Assertible tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Assertible_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Assertible data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Assertible_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Assertible data")
    print(result.messages[-1].content)

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 Assertible. 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 Assertible 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 Assertible MCP in AutoGen

One agent triggers a run using `run_service_tests` while another analyzes the results through the AutoGen MCP adapter. They discuss the failures to determine if a deployment should be blocked.

Yes, an agent can call `sync_specification` with your latest OpenAPI file. This ensures all agents in the conversation are testing against the correct API endpoints.

When `create_deployment` returns a failure, the monitoring agent alerts the coordinator agent. They then run targeted diagnostics to find the broken endpoint.

No, `validate_json` does not require any tokens. Your agents can use it freely to check payload formats during their debugging conversations.

Your execution logs and test results are processed in ephemeral MCP sandboxes that wipe clean instantly. Vinkius never stores your Assertible tokens or API payloads, keeping your testing pipeline completely 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