How to Use the Archbee MCP in Mastra AI

Q: How do I register Archbee tools within a Mastra AI agent?

Initialize the MCPClient with your server URL, call listTools(), and spread the results into your agent's tool array. This exposes functions like createupdatedoc directly to your agent's execution loop.

Q: Can I require human approval before Mastra AI publishes to Archbee?

Yes, set requireToolApproval to true for sensitive operations like publishspace or deletespace. The workflow pauses until an administrator approves the action.

Q: Does this MCP Server support conditional branching based on document content?

Yes, you can design workflows that fetch text using getdoc, inspect the content, and branch to different actions based on what the agent finds.

Build resilient documentation pipelines in Mastra AI that sync OpenAPI schemas and manage Archbee spaces automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Archbee MCP to Mastra AI

Create your Vinkius account to connect Archbee 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 Archbee with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate API sync workflows with Mastra AI

The `sync_openapi` tool updates your developer portal schemas whenever your CI/CD pipeline triggers a new build. Mastra AI coordinates this operation, running `info_openapi` first to check the current state before pushing any new endpoints. If the synchronization fails due to network issues, the workflow engine automatically retries the operation with exponential backoff. This ensures your technical documentation never drifts from your actual codebase when using this MCP Server.

Staged document reviews using MCP Server suggestions

The `merge_suggestion` tool applies proposed documentation edits only after they pass your specified workflow checks. Mastra AI manages this review cycle by queuing suggestions and alerting team leads before final publication. Your agent analyzes incoming edits, uses `discard_suggestion` to reject low-quality drafts, or merges approved changes. This keeps your technical content accurate without requiring manual copy-pasting from pull requests.

Structure and organize space layouts dynamically

The `create_space_group` tool builds organized structures for your API references and user guides based on your product categories. The agent evaluates your current documentation hierarchy and uses `create_space` to spin up new areas as needed. Program conditional branches to handle empty spaces by automatically running `import_content`. This prevents broken or incomplete developer portals from going live.

Setup guide

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

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

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

Initialize the `MCPClient` with your server URL, call `listTools()`, and spread the results into your agent's tool array. This exposes functions like `create_update_doc` directly to your agent's execution loop.

Yes, set `requireToolApproval` to true for sensitive operations like `publish_space` or `delete_space`. The workflow pauses until an administrator approves the action.

The framework features a built-in workflow engine that handles retries for tools like `upload_file`. You can define custom error-handling paths to notify your team if an upload fails.

Yes, you can design workflows that fetch text using `get_doc`, inspect the content, and branch to different actions based on what the agent finds.

Your API keys live in your local environment variables and are never sent to external servers. The MCP Server handles authentication locally, ensuring your proprietary technical guides and schemas remain private.

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