How to Use the Glean MCP in Mastra AI

Q: How do I register the Glean MCP Server inside my Mastra AI agents?

You instantiate the MCPClient with your Vinkius endpoint URL and spread the tools into your Mastra AI agent configuration. The framework automatically discovers tools like searchdocs and exposes them to your agent.

Q: How do I use the Glean chat completion tool in Mastra AI?

You call chatcompletion inside a Mastra AI workflow step to route gateway history and validate outputs. This lets your agent run automated checks on search results before delivering them to users.

Q: Does this integration support human-in-the-loop for document deletion?

Yes, you can set requireToolApproval on the deletedocument tool in Mastra AI. This ensures no agent can remove files from your Glean index without explicit admin authorization.

Build resilient, multi-step enterprise search workflows with Mastra AI and the Glean MCP Server.

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

Build branching search workflows using Mastra AI

The `search_datasource` tool pulls structural properties and account logic from Glean to drive complex decision trees in your Mastra AI agents. If a search query returns empty, your workflow can automatically branch to check alternative datasources or alert an administrator. You register the Glean MCP Server tools inside your Mastra agent configuration with a simple URL pointer. The workflow engine handles the execution, letting you map output data directly to conditional steps without writing custom state machines.

Automate document indexing with built-in retries

The `index_document` tool handles the ingestion of custom files into your Glean search index using native gateway authentication. Mastra AI wraps this tool in its workflow engine, meaning if the Glean API hits a rate limit, the system retries the upload with exponential backoff automatically. This setup ensures your documentation sync never fails silently. You can queue up hundreds of files, and Mastra will process them sequentially, managing the rate limits and auth states in the background.

Verify employee profiles with human approvals

The `search_people` tool queries your corporate directory inside Glean to find specific employee profiles and customer bindings. When integrated with Mastra AI, you can configure `requireToolApproval` to force a human review before your agent sends sensitive directory information to external APIs. This creates a secure boundary for your internal operations. The Mastra agent halts execution, waits for your OK in the console, and then proceeds with the verified profile data.

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-mcp-client",
  servers: {
    "glean-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

You instantiate the `MCPClient` with your Vinkius endpoint URL and spread the tools into your Mastra AI agent configuration. The framework automatically discovers tools like `search_docs` and exposes them to your agent.

Yes, Mastra AI uses its built-in workflow engine to queue and retry calls to tools like `search_datasource` if they hit rate limits. This guarantees your enterprise search pipelines don't crash during peak hours.

You call `chat_completion` inside a Mastra AI workflow step to route gateway history and validate outputs. This lets your agent run automated checks on search results before delivering them to users.

Yes, you can set `requireToolApproval` on the `delete_document` tool in Mastra AI. This ensures no agent can remove files from your Glean index without explicit admin authorization.

Your directory data and employee profiles stay encrypted in transit. The MCP Server executes in a secure, zero-trust sandbox, passing data directly to your Mastra AI deployment without caching sensitive records.

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