How to Use the Ahrefs MCP in AutoGen

Q: How do AutoGen agents access Ahrefs tools?

You install autogen-extmcp and use the McpToolAdapter to load the tools. Pass the output of mcpservertools directly into your AssistantAgent constructor so they can immediately call Ahrefs endpoints.

Q: Can I have one AutoGen agent pull Ahrefs keywords while another writes the content?

Yes. You can assign listkeywordideas to a research agent, which then passes the metrics to a separate writing agent. They will coordinate and debate the best keywords to target.

Q: Do I need to write custom JSON schemas for these SEO tools?

No. The McpToolAdapter automatically translates the schema of the Ahrefs MCP Server into the format that AutoGen expects. Your agents read the parameters and execute calls without manual mapping.

Run multi-agent SEO debates and backlink audits by connecting Ahrefs to your AutoGen framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ahrefs MCP to AutoGen

Create your Vinkius account to connect Ahrefs 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 Ahrefs with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate your organic keyword strategy

Use `list_organic_keywords` and `get_keyword_overview` to feed real-time search volume and ranking data directly into your agent debates. One AutoGen agent can propose a list of target terms while an adversarial agent uses historical search volume from `get_keyword_volume_history` to challenge whether those trends are actually dying out. Instead of a single model guessing what works, your agents argue over actual numbers. They build a solid SEO strategy based on cold, hard metrics, adjusting their plans before presenting a finalized recommendation to you.

Run deep backlink analysis using this MCP Server

The Ahrefs MCP Server gives your multi-agent system direct access to backlink profiles via `list_backlinks` and `list_broken_backlinks`. Your technical SEO agent can pull broken links while a PR agent drafts outreach emails to fix them, all within the same AutoGen run. By letting agents cross-reference `get_backlinks_stats`, you eliminate manual spreadsheet work. The agents check which domains are worth targeting and flag toxic links without you writing a single line of custom integration code.

AutoGen agents dissect competitor top pages

Use `list_top_pages` and `get_domain_overview` to let your agents map out a competitor's organic footprint. Your strategist agent identifies high-value pages, while your content writer agent uses `list_keyword_ideas` to draft outlines that target those exact gaps. This setup turns passive data into an active strategy session. The agents look at search engine results pages using `get_serp_overview`, debate why a competitor ranks first, and output a structured plan to beat them.

Setup guide

Set up Ahrefs 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 Ahrefs 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="Ahrefs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You install `autogen-ext[mcp]` and use the `McpToolAdapter` to load the tools. Pass the output of `mcp_server_tools` directly into your `AssistantAgent` constructor so they can immediately call Ahrefs endpoints.

Yes. You can assign `list_keyword_ideas` to a research agent, which then passes the metrics to a separate writing agent. They will coordinate and debate the best keywords to target.

Yes. You can connect your agents via either transport method. The `StreamableHttpServerParams` class handles the connection details so your conversational workflows run without interruption.

No. The `McpToolAdapter` automatically translates the schema of the Ahrefs MCP Server into the format that AutoGen expects. Your agents read the parameters and execute calls without manual mapping.

Your API tokens and domain query histories are never stored or inspected. They run inside an isolated, ephemeral V8 sandbox on Vinkius, meaning your private SEO research and credentials stay completely secure.

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