Vinkius
Sally logo
Vinkius
Vinkius runs on AutoGen

How to Use the Sally MCP in AutoGen

Debate your frontline workflows with AutoGen. Let agents negotiate project tasks and team comments using the Sally MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Sally MCP on Cursor AI Code Editor MCP Client Sally MCP on Claude Desktop App MCP Integration Sally MCP on OpenAI Agents SDK MCP Compatible Sally MCP on Visual Studio Code MCP Extension Client Sally MCP on GitHub Copilot AI Agent MCP Integration Sally MCP on Google Gemini AI MCP Integration Sally MCP on Lovable AI Development MCP Client Sally MCP on Mistral AI Agents MCP Compatible Sally MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on AutoGen

Connect Sally MCP to AutoGen

Create your Vinkius account to connect Sally to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Key Capabilities

Consensus-driven tasks with AutoGen

One agent proposes a change via `create_task` while another checks the project constraints. They debate until they agree on the priority level. This ensures every task created is verified by multiple perspectives. You avoid the errors that happen when a single agent makes decisions in isolation.

Negotiate comments using AutoGen agents

Agents use `add_comment` to discuss project blockers. They simulate a real team conversation to resolve issues before posting the final update. This keeps your communication professional and accurate. You get a record of the deliberation process attached to every task.

Multi-agent project oversight

Assign a security agent to monitor `get_timesheet_report` for anomalies. If it finds an issue, it challenges the performance agent to justify the project hours. This keeps your operations transparent. The agents hold each other accountable, using the MCP server as their shared source of truth.

Setup guide

Set up Sally MCP in AutoGen

Prerequisites

  • Python 3.10+ installed
  • autogen-ext[mcp] package
  • Active Vinkius subscription with a valid endpoint token
  1. 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. 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. 3

    Run your agent

    Pass the tools to AssistantAgent and call agent.run(). The agent invokes Sally 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="Sally_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 Sally MCP in AutoGen

The McpToolAdapter distributes tools to all agents. They can call functions like `list_projects` collectively during a conversation.
They can. If one agent updates a task, another can check the status and flag it for review if it violates your rules.
All tool calls are ephemeral. Your workspace data is never stored by the agents; it is only used during the active negotiation.
Yes. You can use Streamable HTTP to ensure your agents receive real-time updates as they negotiate.
Only to the agents you authorize. You control which agent gets the `get_profile` tool in the constructor.

Start using the Sally MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 12 tools

We've already built the connector for Sally. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.