How to Use the Legito MCP in Vercel AI SDK

Q: How do I handle Legito rate limits within a Vercel AI SDK edge function?

You handle them by wrapping your updatedocumentversiondata calls in standard fetch retries. Since Vercel AI SDK runs on edge runtimes, keep your execution window tight to avoid edge timeout limits.

Q: Can my Vercel AI SDK agent download generated PDF files from Legito?

Yes, the agent calls downloaddocumentversion to fetch the raw file bytes. You can then stream this buffer directly to the user's browser or save it to your local storage.

Q: How does Legito integrate with Vercel AI SDK for user group synchronization?

The MCP server exposes addusertogroup and removeuserfromgroup to manage your team hierarchy. Your app can trigger these tools dynamically based on Next.js auth events.

Q: Do I need to write custom API wrappers for Legito document records?

No, the MCP server provides direct access via listdocumentrecords and updatedocumentrecord. You just pass the tools block to the SDK and let the model handle the JSON payload.

Run Legito document workflows via MCP directly inside your Vercel AI SDK application with zero loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Legito MCP to Vercel AI SDK

Create your Vinkius account to connect Legito to Vercel AI SDK 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 Legito with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic permission updates with Vercel AI SDK

The `update_user_permissions` tool modifies document access rights instantly during an active chat session. Your Vercel AI SDK client calls this MCP Server endpoint to grant or revoke access as the conversation unfolds. Because the client works within Edge functions, execution stays under 50ms. You can chain `share_with_user` and `remove_share_from_user` calls based on the user's subscription state without spin-up delays.

Automate live Legito document creation

The `create_document_version_data` tool lets your app initiate legal templates directly from user inputs. You pass the template details to the LLM, which triggers the generation process without making the user wait for a page refresh. By feeding the tool output directly into your streaming UI, the end-user watches the document structure build in real-time. This bypasses the typical API latency that kills conversion rates on contract generation portals.

Instant workspace and template discovery

The `list_template_suites` tool exposes your entire Legito template library to your streaming frontend. Your AI client reads this list to suggest the exact contract template a user needs based on their prompt. Users can filter by jurisdiction using `list_countries` or check formatting with `list_advanced_styles`. The SDK renders these options as interactive UI components the moment the model returns the payload.

Setup guide

Set up Legito MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Legito tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Legito transactions",
});

console.log(text);
await mcpClient.close();

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 Legito. 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 Legito 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 Legito MCP in Vercel AI SDK

You handle them by wrapping your `update_document_version_data` calls in standard fetch retries. Since Vercel AI SDK runs on edge runtimes, keep your execution window tight to avoid edge timeout limits.

Yes, the agent calls `download_document_version` to fetch the raw file bytes. You can then stream this buffer directly to the user's browser or save it to your local storage.

The MCP server exposes `add_user_to_group` and `remove_user_from_group` to manage your team hierarchy. Your app can trigger these tools dynamically based on Next.js auth events.

No, the MCP server provides direct access via `list_document_records` and `update_document_record`. You just pass the tools block to the SDK and let the model handle the JSON payload.

Your document records and user permission lists remain strictly inside the Legito secure cloud. The Vinkius MCP gateway only passes the raw JSON payloads through an ephemeral V8 sandbox, never storing your legal drafts or user keys.

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