How to Use the Upstream Lens MCP in CrewAI

Q: How do I structure a workflow analyzing project status using Upstream Lens and CrewAI?

You assign specialized roles: Agent A calls listprojectobservations. Agent B then analyzes the output, flagging any records that are older than 90 days. The crew handles this full cycle autonomously.

Q: Can CrewAI handle metadata retrieval when using Upstream Lens?

Yes. You can assign an agent to run getorganizationinfo as a preparatory step before any other analysis. This ensures the foundational organizational data is available for all team members.

Q: What happens if I need to list projects using Upstream Lens and CrewAI?

The crew runs listprojects, getting a comprehensive list of environmental sites. A moderator agent can then take this output and decide whether to escalate the findings or move on to deeper analysis.

Q: Can I monitor API health before running my primary tasks using Upstream Lens and CrewAI?

You should include a pre-run step calling checkapihealth. If the initial status check fails, the crew can be programmed to halt operations immediately.

Build autonomous operations monitoring oil and gas data from Upstream Lens using CrewAI's specialized agent teams.

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 CrewAI

Create your Vinkius account to connect Upstream Lens to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Field Monitoring

CrewAI specializes agents for this. One agent can run `list_projects` to identify environmental sites, and a second agent can use that list to call `get_property_details` for each location. The shared memory ensures that the initial project list is available for all subsequent analysis steps.

Coordinated Data Reporting

You can set up a crew where one agent gathers historical notes using `list_project_notes`, filtering by date. A second, specialized agent then analyzes those records for key findings. This sequential execution models how real-world teams share and act on critical data points.

Comprehensive Asset Tracking

The MCP Server offers several tools for tracking assets. You can use `list_portfolios` to gather a full list, which an agent then passes to another tool that retrieves imagery layers via `list_property_imagery`. This allows the crew to build a complete picture of physical and financial assets.

Setup guide

Set up Upstream Lens MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Upstream Lens tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Upstream Lens Analyst",
    goal="Access and analyze Upstream Lens data via MCP.",
    backstory="Expert analyst with direct Upstream Lens access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Upstream Lens transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Upstream Lens Analyst",
        goal="Access and analyze Upstream Lens data via MCP.",
        backstory="Expert analyst with direct Upstream Lens access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Upstream Lens transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign specialized roles: Agent A calls `list_project_observations`. Agent B then analyzes the output, flagging any records that are older than 90 days. The crew handles this full cycle autonomously.

Yes. You can assign an agent to run `get_organization_info` as a preparatory step before any other analysis. This ensures the foundational organizational data is available for all team members.

The crew runs `list_projects`, getting a comprehensive list of environmental sites. A moderator agent can then take this output and decide whether to escalate the findings or move on to deeper analysis.

You should include a pre-run step calling `check_api_health`. If the initial status check fails, the crew can be programmed to halt operations immediately.

You must first provide a specific property identifier. The agent then invokes `list_property_imagery` with that ID to retrieve the layer options.

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