How to Use the Raven Tools MCP in Mastra AI

Q: How do I handle Mastra AI workflow retries for Raven Tools?

Wrap tools like getsiteaudit in Mastra's step configuration with a backoff policy. The engine retries the API call if it encounters a network timeout.

Q: Can Mastra AI agents automatically add keywords to Raven Tools?

Yes, you can register addkeyword as an agent tool. The agent evaluates search intent and appends high-value phrases to your tracking campaign autonomously.

Q: How do I restrict Mastra AI from deleting keywords in Raven Tools?

Exclude removekeyword from the list of tools you pass to the MCP client constructor. This keeps your keyword lists safe even if the agent goes off course.

Q: Does the Mastra AI integration support multi-project setups?

Yes, listprojects retrieves all active domains from your account. Your workflow can iterate through this list, running getrankall for every single project sequentially.

Build self-healing SEO workflows in Mastra AI using automated keyword tracking and site audits.

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 Mastra AI

Create your Vinkius account to connect Raven Tools to Mastra AI — 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated SEO Recovery Workflows

`get_rank` serves as the primary trigger in your Mastra AI state machine to detect ranking drops. When a target keyword slips below position ten, the workflow automatically branches to run an audit. You configure the agent to execute `get_site_audit` the second a drop occurs. If the audit fails due to temporary rate limits, Mastra's built-in exponential backoff retries the tool without failing the entire run.

Multi-Step Link Analysis

`get_links` pulls backlink profiles directly into your Mastra agent's memory. The workflow engine evaluates the quality of incoming links and flags toxic domains before writing them to your tracking database. Using `list_keywords` alongside link analysis lets the agent map backlink drops to specific keyword fluctuations. You build a closed-loop system that flags lost links and initiates outreach steps without manual intervention.

Safe Competitor Tracking via Mastra AI MCP Server

`add_competitor` requires human approval before modifying your active tracking list in Raven Tools. You configure Mastra's `requireToolApproval` flag to pause the workflow until an analyst signs off on the new competitor domain. This setup prevents the agent from burning your API limits on irrelevant sites. Once approved, `list_competitors` verifies the update, and the workflow resumes its scheduled tracking routine.

Setup guide

Set up Raven Tools MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Raven Tools tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "raven-tools-mcp-client",
  servers: {
    "raven-tools-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Raven Tools Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Raven Tools tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Raven Tools transactions"
);
console.log(result.text);

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 Mastra AI

Wrap tools like `get_site_audit` in Mastra's step configuration with a backoff policy. The engine retries the API call if it encounters a network timeout.

Yes, you can register `add_keyword` as an agent tool. The agent evaluates search intent and appends high-value phrases to your tracking campaign autonomously.

Exclude `remove_keyword` from the list of tools you pass to the MCP client constructor. This keeps your keyword lists safe even if the agent goes off course.

Yes, `list_projects` retrieves all active domains from your account. Your workflow can iterate through this list, running `get_rank_all` for every single project sequentially.

All keyword strings and competitor domains are processed in memory inside the ephemeral V8 sandbox. No persistent storage is used, keeping your proprietary SEO campaigns safe from external exposure.

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