How to Use the Glean MCP in Mastra AI

Q: Can I use Mastra AI to search Glean datasources conditionally?

Yes, you can. You run searchbydatasource inside a Mastra AI workflow step to query specific platforms like Confluence or Google Drive based on the user's input.

Q: Does Mastra AI support human approval for Glean indexing?

Yes. You set requireToolApproval on tools like indexdocument or bulkindexdocuments to require manual confirmation before files are written to your corporate database.

Q: How do I check if the MCP connection is active?

You run checkgleanstatus as the first step in your workflow execution. This prevents your agents from running complex search chains if the underlying service is temporarily unreachable.

Build resilient, self-healing workspace search workflows with Mastra AI and Glean.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glean MCP to Mastra AI

Create your Vinkius account to connect Glean 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 Glean with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mastra AI indexes new team files with auto-retries

This automation uses `index_document` to insert new corporate files into your central index. If a legacy API rate limit pauses the sync, the Mastra AI workflow engine catches the error and schedules an automatic retry using exponential backoff. You don't write any custom queuing code. The framework tracks the state of each document run and guarantees that your index stays fresh without manual intervention.

Run conditional workspace lookups with this MCP Server

This integration runs `search_people` to verify employee profiles before routing internal support tickets. If Mastra AI finds the person, it branches to `list_collections` to match them with their team's specific document folders. If the search returns no results, the agent automatically escalates the ticket to an admin. This ensures your automated workflows never get stuck in an infinite loop due to missing data.

Safely remove stale files in bulk

This feature uses `delete_document` within an MCP workflow to clean up deprecated project spaces. The workflow first calls `get_collection` to verify the folder's age before executing any delete commands. You can require human approval for these destructive actions. The Mastra AI framework pauses the run, alerts a manager, and only triggers the deletion once it receives a secure confirmation.

Setup guide

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

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

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

Yes, you can. You run `search_by_datasource` inside a Mastra AI workflow step to query specific platforms like Confluence or Google Drive based on the user's input.

You configure your Mastra AI agents with retry policies. If a bulk action like `bulk_index_documents` hits an API limit, the framework automatically pauses and retries the request later.

Yes. You set `requireToolApproval` on tools like `index_document` or `bulk_index_documents` to require manual confirmation before files are written to your corporate database.

You run `check_glean_status` as the first step in your workflow execution. This prevents your agents from running complex search chains if the underlying service is temporarily unreachable.

Yes, because this MCP Server processes all your internal documents and communication logs inside an isolated V8 sandbox. Your credentials and indexed files are never cached on external servers or used for model training.

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