How to Use the Raven Tools MCP in OpenAI Agents SDK

Q: Can Raven Tools handle multiple projects for an OpenAI Agents SDK agent?

Yes. Your agent can call listprojects to see everything available and then pick the right one for getproject. It keeps your multi-client workflow organized.

Bring Raven Tools into your OpenAI Agents SDK production pipeline for automated SEO monitoring and site health tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Raven Tools MCP to OpenAI Agents SDK

Create your Vinkius account to connect Raven Tools to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Raven Tools with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate rank tracking in OpenAI Agents SDK

Feed your agent a list of domains and have it run `get_rank_all` whenever you need a pulse check on search performance. Your agent handles the data retrieval without you manually clicking through dashboards. It manages keyword lists using `add_keyword` and `remove_keyword` based on the trends it detects in your reports. You keep your focus on strategy while the code handles the data entry.

Verify technical health with an MCP Server

Run `get_site_audit` to have your agent identify broken links or crawl errors that hurt your search visibility. It surfaces specific technical issues directly in your agent's reasoning trace. This gives you immediate visibility into site health. You catch issues before they turn into major traffic drops for your clients.

Analyze backlinks with your agent

Use `get_links` to pull backlink profiles into your agent's context window. It parses the data to find new opportunities for your outreach team. Your agent cross-references this with `list_projects` to ensure it targets the right site. It turns raw link data into actionable tasks for your team.

Setup guide

Set up Raven Tools MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Raven Tools tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Raven Tools tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Raven Tools tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Raven Tools Agent",
            instructions="You have access to Raven Tools tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Raven Tools. 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 Raven Tools 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 Raven Tools MCP in OpenAI Agents SDK

You initialize the server by passing the endpoint to the agent constructor. Use the `MCPServerStreamableHttp` class to link the two, ensuring you enable `cacheToolsList` for better performance.

Yes. Your agent can call `list_projects` to see everything available and then pick the right one for `get_project`. It keeps your multi-client workflow organized.

The agent will catch the error since you are running in a production environment. Use `check_raventools_status` at the start of your workflow to verify the connection before you execute complex tasks.

Vinkius manages the connection via an ephemeral sandbox. Only your authenticated agent interacts with the `get_site_audit` or `get_rank` data, keeping your private ranking metrics isolated from other processes.

You can filter the tool list before passing it to the agent constructor. Only give the agent access to the tools it actually needs for its specific task.

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