How to Use the Fulcrum MCP in Mastra AI

Q: How do I start using the Fulcrum MCP with Mastra AI?

Install the @mastra/mcp package from npm. When you define your agent, create a new MCPClient and point it to your Vinkius server URL. Mastra AI discovers the available Fulcrum tools automatically.

Q: Can a Mastra AI agent run complex SQL against Fulcrum?

Yes, the queryrecordssql tool is included. Your Mastra AI agent can construct and run SQL to perform aggregations or joins that aren't possible with the basic record listing tools.

Q: Can I require human approval before a Mastra AI agent modifies Fulcrum data?

You can. Mastra AI's framework has a requireToolApproval option. This makes the agent pause and wait for a person to confirm before it executes a destructive tool like createrecord.

Build bulletproof Fulcrum workflows with Mastra AI. Your agent can handle API errors, retry operations, and execute complex logic automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fulcrum MCP to Mastra AI

Create your Vinkius account to connect Fulcrum 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 Fulcrum with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Records That Don't Fail

When your agent needs to add data to Fulcrum, it uses the `create_record` tool. If the Fulcrum API is busy or there's a network glitch, Mastra AI's engine automatically retries the operation with exponential backoff. You don't write that logic; it's just part of the framework. This is ideal for critical data coming from the field that you absolutely cannot lose.

Run Data Syncs with Conditional Logic

Mastra AI lets you build workflows with branches. For example, you can have an agent `query_records_sql` for new entries. If records are found, it uses `get_record_details` to check a status field. If that status is 'pending_approval', the agent's next step is to notify a manager. This turns your agent from a simple command-runner into a real process engine. You can map out your entire Fulcrum data validation and notification process right in a Mastra AI workflow, and this MCP server provides the tools to get it done.

Automate Audits and Maintenance

Build a workflow that runs on a schedule. Your agent can call `list_organization_members` and compare the list against your company directory. Or it can use `list_webhooks` to check for unauthorized changes to your integrations. If the agent finds something wrong, Mastra AI's engine can trigger another action—like sending an alert or even attempting a fix. The `requireToolApproval` feature lets you add a human-in-the-loop check before any changes to your Fulcrum data are committed.

Setup guide

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

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

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

Install the `@mastra/mcp` package from npm. When you define your agent, create a `new MCPClient` and point it to your Vinkius server URL. Mastra AI discovers the available Fulcrum tools automatically.

Yes, the `query_records_sql` tool is included. Your Mastra AI agent can construct and run SQL to perform aggregations or joins that aren't possible with the basic record listing tools.

Mastra AI has a built-in workflow engine with automatic retries and exponential backoff. If a call to a Fulcrum tool like `create_record` fails, the agent retries it automatically. You don't have to code any of that yourself.

You can. Mastra AI's framework has a `requireToolApproval` option. This makes the agent pause and wait for a person to confirm before it executes a destructive tool like `create_record`.

Your Fulcrum data—form records, user lists, and schemas—is only accessed for the specific task your agent is running. Vinkius processes each tool call in an isolated, short-lived environment, and your Fulcrum API key is encrypted and never exposed.

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