How to Use the Knackly MCP in Mastra AI

Q: How do I initialize Knackly in Mastra AI?

Install @mastra/mcp@latest. Instantiate new MCPClient with your server URL, then call mcpClient.listTools() and spread them into your Mastra Agent's tool array.

Q: Can Mastra AI require human approval before generating a Knackly contract?

Yes. You configure requireToolApproval on the agent. A human reviews the generation payload before the workflow sends it to the API.

Q: How do I list previous entries using the API?

Your workflow calls listdatarecords for a specific model. You can loop through the results and pass specific IDs to getrecorddetails for deeper inspection.

Build resilient document automation workflows with Mastra AI and handle legal logic failures gracefully.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knackly MCP to Mastra AI

Create your Vinkius account to connect Knackly 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 Knackly with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain document logic

Legal drafting breaks when inputs change halfway through. Your MCP workflow queries `list_workspaces` and `list_catalogs` before attempting any generation. If a workspace is missing, the workflow branches to notify an admin instead of failing silently. Next, the workflow hits `list_data_models` to validate required fields. If the upstream data source missed a variable, Mastra's retry logic kicks in to fetch the missing information before proceeding.

Execute records via Mastra AI

Once the data is clean, your workflow triggers `create_data_record`. This applies conditional text rules to your payload. If the API times out during a massive contract build, Mastra automatically retries with exponential backoff. You then add a validation step. The workflow calls `get_record_details` to ensure the submitted data perfectly matches the required model before moving to the next node in your pipeline.

Monitor outputs with this MCP Server

Asynchronous document assembly requires strict monitoring. Your agent can run `list_webhooks` to confirm your server is registered to receive completion events. When the event fires, a separate workflow branch uses `list_generated_documents` to pull the compiled PDFs and route them to your client portal. No manual paralegal review required.

Setup guide

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

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

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

Install `@mastra/mcp@latest`. Instantiate `new MCPClient` with your server URL, then call `mcpClient.listTools()` and spread them into your Mastra Agent's tool array.

Yes. You configure `requireToolApproval` on the agent. A human reviews the generation payload before the workflow sends it to the API.

Mastra auto-detects the transport. It handles either Streamable HTTP or SSE connections to the Vinkius endpoints without manual configuration.

Your workflow calls `list_data_records` for a specific model. You can loop through the results and pass specific IDs to `get_record_details` for deeper inspection.

Vinkius forces a zero-trust architecture. When your workflow pushes proprietary business terms or financial numbers to the MCP endpoint, the ephemeral container processes the transport and immediately terminates. Nothing is cached.

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