How to Use the Keywords AI MCP in Mastra AI

Q: How do I add Keywords AI tools to my Mastra AI agent?

Install @mastra/mcp@latest. Instantiate MCPClient with your server URL, run listTools(), and spread the results into your agent's tool array.

Q: Does Mastra AI support human approval for Keywords AI cost checks?

You can flag getcredits or getusagestats with requireToolApproval. The workflow stops and waits for a developer to manually approve the check before proceeding.

Build resilient LLM monitoring workflows with Mastra AI and catch provider failures before they break your app.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keywords AI MCP to Mastra AI

Create your Vinkius account to connect Keywords AI to Mastra AI 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 Keywords AI with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate API Fallbacks via MCP Server

The Keywords AI MCP Server includes `list_models` and `check_keywordsai_status` to feed your Mastra AI workflows exactly what they need to route traffic. If your primary provider goes down, your workflow evaluates the status check and automatically branches to an available alternative. Mastra handles the exponential backoff if the gateway times out. You build a conditional loop that queries `list_alerts` every few minutes, automatically pausing heavy batch processing until the API stabilizes.

Debug Failed Requests Automatically

`get_request` and `list_requests` let your agent pull exact payload details when an LLM call fails. You don't have to dig through raw server logs. The agent grabs the specific request ID, reads the error response, and drafts a fix. Combine this with Mastra's human-in-the-loop features. If a request throws a strange formatting error, the workflow pauses, requires your approval via `requireToolApproval`, and waits for you to review the raw prompt before retrying.

Enforce Hard Budget Limits

`get_credits` and `get_analytics` provide the hard financial numbers your workflow needs to stop runaway spending. Before running a massive automated evaluation job, Mastra queries your balance via the MCP connection. If the balance drops below a threshold you set, the workflow branches to a halt state and alerts your finance channel. It is a dead-simple way to prevent a rogue script from draining ten thousand dollars over the weekend.

Setup guide

Set up Keywords AI 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 Keywords AI 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: "keywords-ai-mcp-client",
  servers: {
    "keywords-ai-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Keywords AI 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 Keywords AI. 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 Keywords AI 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 Keywords AI MCP in Mastra AI

Install `@mastra/mcp@latest`. Instantiate `MCPClient` with your server URL, run `listTools()`, and spread the results into your agent's tool array.

Yes. You configure exponential backoff directly in your workflow definition. If a tool call times out, the engine waits and tries again without writing custom loop logic.

You can flag `get_credits` or `get_usage_stats` with `requireToolApproval`. The workflow stops and waits for a developer to manually approve the check before proceeding.

The framework auto-detects the transport layer. It negotiates either Streamable HTTP or SSE based on the endpoint configuration provided by Vinkius.

The server touches exact token counts, credit balances, and team member emails. Vinkius enforces zero-trust architecture, meaning your Mastra client connects through a single-use token to an isolated instance that vanishes the moment the workflow completes.

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