How to Use the Sensible MCP in Mastra AI

Q: How does Mastra AI handle failed document extractions in Sensible?

If extractsync fails due to a bad scan, Mastra AI uses its built-in retry logic. If retries fail, your agent can call getauthtokens to flag the document for manual review by an external operator.

Q: Can Mastra AI automatically update Sensible configurations?

Yes. Your agent can call updateconfiguration whenever it detects layout drift. Mastra AI's workflow engine runs these updates programmatically, keeping your extraction accuracy high without manual code changes.

Q: Is there a way to batch-process PDFs using Sensible and Mastra AI?

You can have your Mastra AI agent call generateuploadurl for each file in your queue, then run extractfromurl asynchronously. Mastra's engine tracks each job status and aggregates the results.

Q: How do I test new document layouts in my Mastra workflows?

Your agent can call createdocumenttype to set up a test sandbox. You can then run sample documents through extractsync to verify the extraction schema before publishing.

Automate complex multi-step document workflows with Mastra AI and the Sensible MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sensible MCP to Mastra AI

Create your Vinkius account to connect Sensible 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 Sensible with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated error recovery in Mastra AI workflows

Mastra AI is built for complex, multi-step agent behaviors. When parsing a messy document, your agent can call `extract_sync_with_config` and, if the extraction confidence is too low, automatically trigger a fallback branch. The agent can then call `get_auth_tokens` to generate a temporary review link for a human operator to verify the data. This setup keeps your pipeline moving without crashing. By combining Mastra's workflow engine with the MCP Server, you build self-healing document pipelines that handle blurry scans and missing fields gracefully.

Dynamic schema training with Mastra AI agents

Instead of manually configuring every document variation, let your Mastra AI agent manage the training lifecycle. The agent can use `create_golden` to upload reference documents and `extract_text_from_golden` to analyze text coordinates. This lets your agent programmatically build a highly accurate parser. If the extraction accuracy drops, Mastra's loop can trigger `update_golden` to refine the model. Your agent maintains the parsing quality autonomously, adjusting to layout shifts without developer intervention.

Multi-document portfolio extraction

Handling zip files or combined document packets is notoriously difficult. With this MCP Server, your Mastra AI agent calls `generate_portfolio_upload_url` to upload the entire batch at once. It then runs `extract_portfolio_from_url` to dissect the portfolio into individual, structured JSON objects. Mastra AI coordinates the downstream tasks once the extraction completes. The agent takes the parsed data, runs validation checks, and writes the clean records directly to your database.

Setup guide

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

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

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

If `extract_sync` fails due to a bad scan, Mastra AI uses its built-in retry logic. If retries fail, your agent can call `get_auth_tokens` to flag the document for manual review by an external operator.

Yes. Your agent can call `update_configuration` whenever it detects layout drift. Mastra AI's workflow engine runs these updates programmatically, keeping your extraction accuracy high without manual code changes.

You can have your Mastra AI agent call `generate_upload_url` for each file in your queue, then run `extract_from_url` asynchronously. Mastra's engine tracks each job status and aggregates the results.

Your agent can call `create_document_type` to set up a test sandbox. You can then run sample documents through `extract_sync` to verify the extraction schema before publishing.

All document extractions run inside isolated, single-use V8 environments via the MCP Server. Your sensitive financial and medical documents are processed in memory and never written to persistent disk storage, ensuring strict data isolation.

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