How to Use the Postscript MCP in AutoGen

Debate your SMS marketing strategy with autonomous agents using AutoGen and the Postscript MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Postscript MCP to AutoGen

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

GDPR Included with Plan

Setup Postscript with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate SMS campaigns with AutoGen

Assign one agent to watch revenue and another to handle compliance. They use `get_campaign` and `list_keywords` to reach a consensus on the next SMS blast. Conflict leads to better results. One agent might suggest an aggressive send time, while the other blocks it using `list_automations` to avoid quiet-hour violations.

Manage subscriber state via debate

Let your agents reconcile data discrepancies before updating records. They call `get_subscriber` to verify status before the executor triggers `update_subscriber`. Errors are caught early. If one agent proposes a change that violates a rule, the other flags it based on the account details fetched from `get_account_info`.

Coordinate webhook logic

Agents discuss whether to add or remove webhooks based on current traffic. They use `list_webhooks` to audit the current setup before calling `delete_webhook`. Decisions are audited. Every step of the debate is logged, showing why the agents chose to modify your webhook configuration.

Setup guide

Set up Postscript 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 Postscript 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="Postscript_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Yes, you provide the tool list to the agent group. They decide which agent is best suited to call `list_subscribers` based on the current task.

They use their internal reasoning loop to debate the best path. If one agent finds a campaign issue, it presents the data from `get_campaign` to the other for review.

You control the permissions. By limiting the tools available to specific agents, you ensure only authorized actions like `create_subscriber` occur.

You can set up a 'Compliance Agent' to review every action. It checks tool calls against your internal policies before allowing the final execution.

The data stays within the conversation flow. It is processed in memory during the debate and discarded once the agents reach their conclusion.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python