4,500+ servers built on MCP Fusion
Vinkius
Glean logo
Vinkius
OpenAI Agents SDK logo

How to Use the Glean MCP in OpenAI Agents SDK

Feed Glean enterprise search directly into your production OpenAI Agents SDK pipelines with zero config.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Glean MCP on Cursor AI Code Editor MCP Client Glean MCP on Claude Desktop App MCP Integration Glean MCP on OpenAI Agents SDK MCP Compatible Glean MCP on Visual Studio Code MCP Extension Client Glean MCP on GitHub Copilot AI Agent MCP Integration Glean MCP on Google Gemini AI MCP Integration Glean MCP on Lovable AI Development MCP Client Glean MCP on Mistral AI Agents MCP Compatible Glean MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
OpenAI Agents SDK

Connect Glean MCP to OpenAI Agents SDK

Create your Vinkius account to connect Glean to OpenAI Agents 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

Safe Enterprise Search for OpenAI Agents SDK

Let your production OpenAI Agents SDK pipelines search Glean company knowledge without losing control. This MCP Server exposes tools like `search` and `search_by_datasource` directly to your OpenAI Agents SDK runtime. Built-in OpenAI Agents SDK guardrails validate every Glean query before execution, protecting your corporate index. If a Glean tool call fails, your OpenAI Agents SDK pipeline safely halts or hands off to a human. You get clean Glean search results from Confluence or Slack, fully tracked on your OpenAI Agents SDK dashboard.

Instant Indexing and Document Control

Keep your OpenAI Agents SDK context window fresh by managing Glean documents in real-time. Your OpenAI Agents SDK pipelines use `index_document` and `bulk_index_documents` to push data directly into your Glean index. When files go stale, your OpenAI Agents SDK system calls `delete_document` to purge them from Glean. This active Glean indexing prevents stale context errors in your OpenAI Agents SDK runs. You control exactly what gets written back to the Glean index, keeping your OpenAI Agents SDK search pool clean.

Directory Lookups and Status Checks

Before executing complex OpenAI Agents SDK handoffs, verify your Glean MCP Server health. Your OpenAI Agents SDK system runs `check_glean_status` to confirm Glean is online. Once verified, your OpenAI Agents SDK agent uses `search_people` to route tasks to the right Glean-indexed expert. This setup ensures your OpenAI Agents SDK system never hangs waiting on a dead Glean API. It uses live Glean directory data to resolve OpenAI Agents SDK ownership issues.

Setup guide

Set up Glean MCP in OpenAI Agents SDK

Prerequisites

  • Python 3.10+ installed
  • openai-agents package (pip install openai-agents)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install the SDK

    Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.

  2. 2

    Connect via SSE transport

    Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Glean tools at runtime.

  3. 3

    Create your Agent

    Pass the MCP to Agent(mcp_servers=[server]). The agent receives Glean tools as native definitions — JSON schemas resolve automatically.

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Glean tools and returns structured results. Copy the full example on the right to get started.

agent.py
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Glean Agent",
            instructions="You have access to Glean tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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.

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 OpenAI Agents SDK

You pass the server connection as an MCP server parameter during agent initialization. The SDK automatically reads the schema and registers tools like `search` and `chat` as active agent functions.
Yes, you control this at the server transport layer or via the agent's constructor. You can limit the agent to read-only actions like `search_by_datasource` and block write actions like `delete_document`.
The SDK catches the failure and returns the error trace to your dashboard. You can configure a fallback agent to run `check_glean_status` to see if the issue is network-related.
The agent uses `list_collections` or `get_collection` to navigate structured folders step by step. This prevents your OpenAI Agents SDK pipelines from hitting token limits on massive query returns.
All search queries and indexed document payloads are processed inside Vinkius's isolated MCP sandbox. The server never stores your private Confluence or Slack content, and only the raw JSON results from `search` are passed back to your OpenAI Agents SDK runtime.

Start using the Glean MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 12 tools

We've already built the connector for Glean. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 12 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.