How to Use the Glean MCP in LangChain

Q: Does this support complex reasoning with multiple tools?

Absolutely. You can chain search and chat calls to build sophisticated reasoning flows that answer multi-part questions.

Q: How do I handle connection issues with the server?

Run checkgleanstatus at the start of your chain. If it fails, your agent can catch the error and alert you immediately.

Chain Glean tools directly into your LangChain pipelines for precise, multi-step enterprise reasoning.

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 LangChain

Create your Vinkius account to connect Glean to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic tool chaining in LangChain

You define complex workflows where the output from `search` flows directly into subsequent processing nodes. This allows your agent to fetch raw company data and refine it through your own logic gates without manual intervention. Every step of the process is visible in LangSmith. You track exactly how the `search_people` results inform the next decision in your chain, ensuring the agent stays grounded in factual enterprise data.

Multi-server aggregation

Connect this MCP server alongside your existing databases and APIs within a single LangChain agent. Your agent evaluates which tool to invoke by weighing the immediate context against the required outcome. You avoid bottlenecks by letting the model decide the execution order. It pulls from `list_collections` and `get_document` based on the specific intent of the user's request.

Contextual state management

Use client sessions to maintain state across multiple tool calls in your long-running chains. This keeps the conversation moving without needing to re-fetch the same document metadata repeatedly. When the agent needs specific file details, it triggers `get_document` within the active session. You keep the pipeline stateless or persistent, depending on the requirements of your specific application.

Setup guide

Set up Glean MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Glean tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "glean-alternative-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Glean transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Yes. You simply register the server tools with your agent. It gains the ability to query your internal knowledge base instantly.

LangSmith handles this natively. Every input and output from the server appears in your trace logs for full visibility.

The server respects your existing company permissions. It only returns documents the authenticated user is allowed to see.

Absolutely. You can chain `search` and `chat` calls to build sophisticated reasoning flows that answer multi-part questions.

Run `check_glean_status` at the start of your chain. If it fails, your agent can catch the error and alert you immediately.

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

Mastra AI sdk-typescript

Start using the Glean MCP today

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

Get started