How to Use the NinjaCat MCP in AutoGen

Q: How do I equip my AutoGen agents with NinjaCat tools?

Install the autogen-extmcp package. Use mcpservertools to connect to the NinjaCat MCP Server URL, and pass that list directly to your AssistantAgent constructor.

Q: How do agents handle missing data in NinjaCat using AutoGen?

If getadvertiser returns an error or empty result, the executing agent will report that back to the chat. The other agents will then debate alternative approaches, like searching listadvertisers instead.

Q: Does the MCP server support AutoGen's streamable HTTP transport?

Yes. You configure the StreamableHttpServerParams to maintain a persistent connection while the agents deliberate over the campaign data.

Build negotiating AutoGen agents that audit and retrieve your NinjaCat marketing data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NinjaCat MCP to AutoGen

Create your Vinkius account to connect NinjaCat 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 NinjaCat with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Campaign Reviews

The `list_agency_campaigns` and `list_data_accounts` tools give your AutoGen agents the raw material to debate marketing coverage. A reporting agent can pull the active campaigns while an audit agent checks if the corresponding data accounts are actually connected. They negotiate the discrepancies. If the reporting agent sees a campaign but the audit agent finds no linked data source via `list_data_sources`, they flag the mismatch. You get a consensus-driven alert about broken reporting pipelines before the client notices.

Debate NinjaCat MCP Server Reports

One AutoGen agent calls `list_reports` to see what is scheduled, while a secondary agent uses `get_report_history` to verify what actually executed. They cross-reference the planned output against the historical reality. If a report failed, the agents discuss the next step. One might suggest checking `get_agency_info` for account status, while another might just pull the last successful run's link using `get_report_download_url`. They figure out the fallback plan autonomously.

Autonomous Advertiser Lookups

Give your conversational agents access to `list_advertisers` and `get_advertiser`. When a user asks a complex question about a client's setup, the agents don't just spit out the first answer. They fetch the specific advertiser details and debate the implications of their configuration. A security-focused agent might check `get_me` to verify the current user has the right permissions to view the advertiser. The agents talk it out, ensuring the data retrieval meets your internal access rules before presenting the final summary to the user.

Setup guide

Set up NinjaCat 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 NinjaCat 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="NinjaCat_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Use `mcp_server_tools` to connect to the NinjaCat MCP Server URL, and pass that list directly to your `AssistantAgent` constructor.

Yes. You provide the MCP server toolset to the group chat. The agents decide among themselves who should call `list_data_sources` or `list_reports` based on their assigned personas.

If `get_advertiser` returns an error or empty result, the executing agent will report that back to the chat. The other agents will then debate alternative approaches, like searching `list_advertisers` instead.

Yes. You configure the `StreamableHttpServerParams` to maintain a persistent connection while the agents deliberate over the campaign data.

The server processes raw campaign names, advertiser setups, and report URLs. Vinkius routes this traffic through stateless, single-use sandboxes, ensuring your marketing metadata never persists after the agent finishes its conversation.

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