How to Use the Mozscape MCP in AutoGen

Q: Can I have AutoGen agents negotiate budget limits for Mozscape?

Yes. An agent can call v2usagedata to check the billing status, then argue with other agents to limit expensive calls like fetchmultiplesitemetrics if the quota is running low. This prevents runaway MCP tool execution.

Q: How do AutoGen agents handle conflicting Mozscape link data?

They deliberate. If fetchsitemetrics shows a high Spam Score but fetchbrandauthority is also high, the agents will debate the trade-offs before outputting a final recommendation.

Q: Can I track recently lost linking domains?

Yes. You can use filterrecentlylostdomains to identify domains that stopped linking to you, allowing your team to run quick recovery campaigns.

Coordinate AutoGen agents to debate link-building strategies using real-time Mozscape metrics via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mozscape MCP to AutoGen

Create your Vinkius account to connect Mozscape 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 Mozscape with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate your link profile

This MCP Server allows AutoGen to set up specialized agents that argue over SEO data. A 'Spam Auditor' agent can pull data using `fetch_site_metrics` to flag high spam scores, while a 'Link Builder' agent defends the link using `v2_link_status`. They negotiate until they reach a consensus on whether to disavow. This multi-agent debate ensures you don't make rash decisions based on a single metric, giving you a highly refined strategy.

Run competitive intelligence with AutoGen

Deploy one agent to map competitor weaknesses using `v2_link_intersect` while another analyzes top-performing pages via `v2_global_top_pages`. They combine their findings to propose high-value target lists. This cooperative workflow happens autonomously in the background. The agents refine their target list by running `fetch_brand_authority` to ensure every prospect meets your quality standards.

Validate link equity across complex redirects

Link migrations are messy, but AutoGen agents can divide and conquer. One agent can trace redirect paths using `v2_final_redirect`, while another checks the destination's link equity with `v2_url_metrics`. By comparing notes, the agents can identify lost link juice from broken redirect chains. They will present a clean report of where your equity is leaking and how to patch it.

Setup guide

Set up Mozscape 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 Mozscape 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="Mozscape_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The credentials are managed securely by Vinkius at the MCP Server level. Your AutoGen agents simply call the tools without needing to pass keys back and forth in their conversation.

Yes. An agent can call `v2_usage_data` to check the billing status, then argue with other agents to limit expensive calls like `fetch_multiple_site_metrics` if the quota is running low. This prevents runaway MCP tool execution.

They deliberate. If `fetch_site_metrics` shows a high Spam Score but `fetch_brand_authority` is also high, the agents will debate the trade-offs before outputting a final recommendation.

Yes. You can use `filter_recently_lost_domains` to identify domains that stopped linking to you, allowing your team to run quick recovery campaigns.

Yes. All data processed during the multi-agent debate—including competitor link profiles fetched via `v2_link_intersect`—is handled in an ephemeral MCP environment that is wiped clean immediately after the run.

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