How to Use the Health Gorilla MCP in CrewAI

Q: How would a CrewAI team use Health Gorilla to check for and analyze new lab results?

Set up a "Monitor" agent to periodically call listpatientresults. When it detects a new result, it passes the order ID to an "Analyst" agent, which then uses getlabresults to fetch the data and review it for anomalies.

Q: Is it possible to restrict which Health Gorilla tools each agent in my CrewAI can use?

Yes. By using the toolfilter option when you define the MCP connection for an agent, you can create strict permissions. This allows you to grant submitlaborder to an "Ordering Agent" but restrict a "Billing Agent" to read-only tools.

Assemble autonomous agent crews on CrewAI to manage clinical operations and process lab data from Health Gorilla.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Health Gorilla MCP to CrewAI

Create your Vinkius account to connect Health Gorilla 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 Health Gorilla with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy an Agent Crew for Patient Intake

Stop thinking in terms of a single agent. With CrewAI, you build a specialized team. Assign an "Intake Specialist" agent the task of using `match_patient`. If it can't find a clear match, it delegates the job to a "Registration Agent" that has the sole permission to use `create_patient_record`. This role-based approach is cleaner and more secure. The Intake agent can also be tasked with using `get_patient_demographics` to verify information. Meanwhile, a "Provider Lookup Agent" can use `search_providers` to find the right doctor. They work in concert, each with a specific, limited role.

Build an Autonomous Order Management Crew

Placing a lab order is a job for a crew, not a single agent. A "Clinical Research Agent" can use `search_lab_tests` to identify the correct test codes. It then passes the details to an "Order Placement Agent" whose only tool is `submit_lab_order`. This separation of concerns is a more robust way to build. At the same time, a "Monitoring Agent" runs in the background. Its only job is to periodically call `list_orders` and `get_order_status`. If an order is unexpectedly cancelled or gets stuck, it can trigger an alert or assign a task to another agent to investigate. This is how you build a self-managing system with this MCP server.

Analyze Lab Results with a Specialist Crew

Data retrieval and analysis are two different jobs. Task a "Scout Agent" to constantly poll `list_patient_results` for newly completed tests. Once it finds one, its only job is to fetch the full report using `get_lab_results`. The Scout Agent doesn't analyze anything. It hands the structured result to an "Analyst Agent." This specialist agent's job is to check for values outside the normal range. If it finds an anomaly, it creates a new task for a "Notification Agent" to alert the on-call provider. CrewAI provides the team structure to make this possible.

Setup guide

Set up Health Gorilla 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 Health Gorilla tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Health Gorilla 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="Health Gorilla Analyst",
        goal="Access and analyze Health Gorilla data via MCP.",
        backstory="Expert analyst with direct Health Gorilla access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Health Gorilla 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 Health Gorilla. 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 Health Gorilla 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 Health Gorilla MCP in CrewAI

In your Agent definition, pass your Vinkius server URL directly into the `mcps` list. For more fine-grained control, you can use `MCPServerHTTP` from `crewai.mcp` along with a `tool_filter` to expose only specific Health Gorilla tools to each agent.

Yes, that's a perfect use case. You can create one agent to handle `search_lab_tests`, a second to `submit_lab_order`, and a third to monitor `get_order_status`. They can work sequentially or in parallel to manage the full order lifecycle.

Set up a "Monitor" agent to periodically call `list_patient_results`. When it detects a new result, it passes the order ID to an "Analyst" agent, which then uses `get_lab_results` to fetch the data and review it for anomalies.

Yes. By using the `tool_filter` option when you define the MCP connection for an agent, you can create strict permissions. This allows you to grant `submit_lab_order` to an "Ordering Agent" but restrict a "Billing Agent" to read-only tools.

Your agents will handle patient records, lab orders, and test results. Vinkius ensures your MCP server connection is isolated and ephemeral. The data flows between your CrewAI agents in memory and the Health Gorilla API; it is not persisted on Vinkius servers.

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