How to Use the Merge (Unified Integration API) MCP in AutoGen

Q: Can multiple AutoGen agents call Merge (Unified Integration API) tools simultaneously?

Yes, agents can execute tools like listtickets and listaccounts in parallel during their turn. The server handles concurrent requests within its execution limits.

Q: How do AutoGen agents negotiate rate limits on the Merge (Unified Integration API)?

Agents can query getaccountdetails to check integration status. If a rate limit is approaching, a coordinator agent instructs other agents to delay their queries.

Coordinate multi-agent debates in AutoGen using unified HRIS, ATS, and CRM data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Merge (Unified Integration API) MCP to AutoGen

Create your Vinkius account to connect Merge (Unified Integration API) 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 Merge (Unified Integration API) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve hiring decisions through multi-agent candidate debates

The `list_candidates` and `list_applications` tools deliver structured ATS data straight to your AutoGen agent conversations. One agent can review candidate profiles while a separate compensation agent checks internal salary bands. They debate the hire's viability based on real-time data, negotiating the offer details before presenting a final decision to the user. This consensus-driven approach ensures all hiring decisions are backed by active ATS records.

Audit company structures with an AutoGen MCP Server

The `list_employees` and `list_companies` tools allow multiple agents to audit organizational structures. A compliance agent flags missing manager roles, while an operations agent cross-references active accounts. The agents discuss discrepancies in a shared conversation thread, using the tool outputs to verify facts. You get a fully audited report without manual spreadsheet matching.

Coordinate CRM account mapping across competing agents

The `list_contacts` and `list_accounts` tools expose CRM boundaries to your AutoGen team using this MCP connection. When a new lead is detected, a sales agent and a support agent negotiate who owns the contact. By reviewing active support tickets via `list_tickets`, the support agent can argue for ownership if there is an open issue. The agents resolve the routing conflict autonomously.

Setup guide

Set up Merge (Unified Integration API) 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 Merge (Unified Integration API) 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="Merge (Unified Integration API)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Merge (Unified Integration API) 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="Merge (Unified Integration API)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Merge (Unified Integration API) 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 Merge. 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 Merge (Unified Integration API) 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 Merge (Unified Integration API) MCP in AutoGen

You use the MCP tool adapter to convert the MCP Server tools into AutoGen-compatible schemas. Pass the resulting tool list to your assistant agent constructor to enable endpoints like `list_employees`.

Yes, agents can execute tools like `list_tickets` and `list_accounts` in parallel during their turn. The server handles concurrent requests within its execution limits.

Agents can query `get_account_details` to check integration status. If a rate limit is approaching, a coordinator agent instructs other agents to delay their queries.

The server supports both stdio and streamable HTTP transports. You configure the server parameters inside your Python initialization script.

The MCP Server runs inside a sandboxed V8 environment that isolates all HRIS and ATS payloads. Data is never cached or logged on external servers, keeping sensitive personal info confidential.

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