How to Use the Upstream Lens MCP in LangChain

Q: How do I check API health with Upstream Lens and LangChain?

Just call checkapihealth. It tells you immediately if the connection is good. That's step zero for any complex chain, ensuring your agent doesn't waste time on a broken endpoint.

Q: Can I use Upstream Lens and LangChain to find project details?

Absolutely. First, call listprojects to get the IDs you need. Then pass those IDs directly into getpropertydetails so your agent gets specific feature data for that site.

Q: Does Upstream Lens and LangChain support viewing imagery?

Yes, it does. You can use listpropertyimagery to see what layers are available for a property. This is crucial context when your agent needs visual confirmation of field conditions.

Q: Can I see all available portfolios using Upstream Lens and LangChain?

You just call listportfolios. It immediately returns a list of every portfolio managed within the system. You can then feed that resulting list into another tool for deeper analysis.

Build complex monitoring chains for oil and gas data using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Upstream Lens MCP to LangChain

Create your Vinkius account to connect Upstream Lens 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 Upstream Lens with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step logic with the MCP Server.

Need to know if a project is active? Start by calling `list_projects` to get all environmental sites. Then, use that list to call `get_property_details` for specific features associated with those projects. This sequence lets your agent figure out the full status of an entire site before you even write a single line of code.

Track historical project activity.

`list_project_notes` gives you access to recorded updates, and filtering by date helps narrow down exactly what happened when. Pair this with `list_project_observations` to see the full technical write-up for a given time frame. Your agent can decide which data points are relevant based on whether it's looking at notes or detailed observations.

Analyze organizational structure.

Start with `get_organization_info` to understand the overall metadata for your operation. Once you have that context, you can use `list_portfolios` to see which groups of assets are managed under that umbrella. This workflow lets the agent build a map of everything from corporate structure down to individual asset grouping.

Setup guide

Set up Upstream Lens 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 Upstream Lens 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({
    "upstream-lens-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 Upstream Lens 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 Upstream Lens. 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 Upstream Lens 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 Upstream Lens MCP in LangChain

Just call `check_api_health`. It tells you immediately if the connection is good. That's step zero for any complex chain, ensuring your agent doesn't waste time on a broken endpoint.

Absolutely. First, call `list_projects` to get the IDs you need. Then pass those IDs directly into `get_property_details` so your agent gets specific feature data for that site.

Yes, it does. You can use `list_property_imagery` to see what layers are available for a property. This is crucial context when your agent needs visual confirmation of field conditions.

This MCP Server touches environmental project data, specifically the structured output from `get_organization_info` (metadata) and raw observational text from `list_project_notes`.

You just call `list_portfolios`. It immediately returns a list of every portfolio managed within the system. You can then feed that resulting list into another tool for deeper analysis.

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