Semrush MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Semrush through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Semrush Assistant",
instructions=(
"You help users interact with Semrush. "
"You have access to 8 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Semrush"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Semrush MCP Server
Equip your conversational workflow with the raw data power of Semrush, the industry standard for Digital Marketing visibility. Through this server, your AI can pull immense amounts of SERP forensics directly into the context window. Stop switching tabs to look up keyword difficulty—just command your agent to fetch it seamlessly.
The OpenAI Agents SDK auto-discovers all 8 tools from Semrush through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Semrush, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Deep Domain Forensics (Competitors) — Query
domain_overviewordomain_vs_domainto tell your agent to digest the exact organic search volume differences between you and a rival - Keyword Strategy Building — Hand a seed topic to the LLM and invoke
related_keywords. The AI will compile comprehensive editorial briefs loaded with actual search volumes and CPCs - Backlink Auditing — Track the inbound link profile (
get_backlinks) of external domains to gauge authority natively within chat sessions - Technical SEO Interrogation — Quickly bring your technical
site_auditscore to the AI, asking it to explain what the flagged errors mean and draft instructions to fix missing metadata
The Semrush MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Semrush to OpenAI Agents SDK via MCP
Follow these steps to integrate the Semrush MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 8 tools from Semrush
Why Use OpenAI Agents SDK with the Semrush MCP Server
OpenAI Agents SDK provides unique advantages when paired with Semrush through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Semrush + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Semrush MCP Server delivers measurable value.
Automated workflows: build agents that query Semrush, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Semrush, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Semrush tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Semrush to resolve tickets, look up records, and update statuses without human intervention
Semrush MCP Tools for OpenAI Agents SDK (8)
These 8 tools become available when you connect Semrush to OpenAI Agents SDK via MCP:
domain_overview
Specify the database (e.g., "us", "uk") if targeting a specific region. Get domain SEO overview: rank, organic traffic, paid traffic
domain_vs_domain
Compare two domains SEO side by side
get_backlinks
Get backlink overview for a domain
keyword_overview
Get keyword metrics: volume, CPC, competition, SERP features
organic_keywords
Useful for competitor analysis or performance tracking. Get domain organic keyword positions
related_keywords
Ideal for content planning and SEO expansion. Get related keywords with volume and difficulty
site_audit
Requires a valid Semgrep project ID. Get site audit quality overview for a project
traffic_analytics
Get traffic analytics: visits, bounce rate, pages/visit
Example Prompts for Semrush in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Semrush immediately.
"Pull the foundational organic ranking and paid traffic overview for the domain 'airbnb.com'. Target the US database."
"Find 10 related keywords for the term 'buy mechanical keyboard' including their respective difficulties and search volumes."
"Compare the overarching inbound domain performance between 'coca-cola.com' and 'pepsi.com'."
Troubleshooting Semrush MCP Server with OpenAI Agents SDK
Common issues when connecting Semrush to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Semrush + OpenAI Agents SDK FAQ
Common questions about integrating Semrush MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Semrush with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Semrush to OpenAI Agents SDK
Get your token, paste the configuration, and start using 8 tools in under 2 minutes. No API key management needed.