How to Use the eCompliance MCP in AutoGen

Q: How do I register eCompliance tools with AutoGen?

Install autogen-extmcp. Use mcpservertools with a StreamableHttpServerParams configuration, and pass the resulting tool list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents use eCompliance tools at once?

Yes. The McpToolAdapter handles the schema conversion. Any agent in the conversation with the tools registered can call searchsafetyincidents to gather evidence for their argument.

Q: How do agents handle missing inspection data in AutoGen?

If getinspectiondetails returns an empty set, the agent reports the missing data to the group chat. Another agent can then suggest calling getecompliancemetadata to verify the connection status.

Q: Is employee roster data exposed to the LLM provider?

Yes, when an agent calls listsiteemployees, the names and site IDs are sent to your configured LLM for reasoning. Vinkius secures the transport via an ephemeral, single-use auth token, but you must ensure your LLM provider has a zero-retention policy.

Give your AutoGen agents direct access to the eCompliance MCP Server. Watch them debate safety audits and negotiate corrective actions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eCompliance MCP to AutoGen

Create your Vinkius account to connect eCompliance 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 eCompliance with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate on safety incidents

`get_incident_details` provides the exact investigation notes to your AutoGen chat group. A risk-assessment agent reviews the narrative while a compliance-auditor agent checks the timeline. They argue over the severity. The risk agent might flag a minor cut as a systemic hazard, prompting the compliance agent to run `list_safety_incidents` to find historical precedents. They reach a consensus before alerting human management.

Automate site health audits via MCP Server

The `quick_safety_health_audit` tool hands your agents a top-level summary of all recent site activity. If the numbers look bad, a manager agent assigns a worker agent to dig deeper. The worker agent triggers `list_safety_inspections` to find the exact audits that dragged the score down. This isn't a simple script. It is a dynamic conversation where agents challenge each other's findings until the root cause is isolated.

Negotiate corrective action priorities

`list_corrective_actions` pulls the backlog of required safety fixes into the thread. Your operational agent pushes to delay fixes for production speed, while the safety agent demands immediate resolution. The safety agent pulls data from `list_latest_incidents` to prove that ignoring the fixes is causing active harm. The framework forces them to negotiate a priority list based on hard API data, not assumptions.

Setup guide

Set up eCompliance 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 eCompliance 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="eCompliance_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent eCompliance 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="eCompliance_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent eCompliance 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 eCompliance. 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 eCompliance 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 eCompliance MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration, and pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. The `McpToolAdapter` handles the schema conversion. Any agent in the conversation with the tools registered can call `search_safety_incidents` to gather evidence for their argument.

If `get_inspection_details` returns an empty set, the agent reports the missing data to the group chat. Another agent can then suggest calling `get_ecompliance_metadata` to verify the connection status.

You configure that in the framework. You can set the execution to require human input before calling destructive tools, though the current eCompliance MCP implementation is strictly read-only.

Yes, when an agent calls `list_site_employees`, the names and site IDs are sent to your configured LLM for reasoning. Vinkius secures the transport via an ephemeral, single-use auth token, but you must ensure your LLM provider has a zero-retention policy.

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