Health Gorilla MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Health Gorilla through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Health Gorilla Assistant",
instructions=(
"You help users interact with Health Gorilla. "
"You have access to 12 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Health Gorilla"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Health Gorilla MCP Server
Connect Health Gorilla to any AI agent via MCP.
How to Connect Health Gorilla to OpenAI Agents SDK via MCP
Follow these steps to integrate the Health Gorilla MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 12 tools from Health Gorilla
Why Use OpenAI Agents SDK with the Health Gorilla MCP Server
OpenAI Agents SDK provides unique advantages when paired with Health Gorilla through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Health Gorilla + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Health Gorilla MCP Server delivers measurable value.
Automated workflows: build agents that query Health Gorilla, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Health Gorilla, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Health Gorilla tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Health Gorilla to resolve tickets, look up records, and update statuses without human intervention
Health Gorilla MCP Tools for OpenAI Agents SDK (12)
These 12 tools become available when you connect Health Gorilla to OpenAI Agents SDK via MCP:
cancel_lab_order
Orders in "received" or "pending" status can typically be cancelled. Orders already in "collected" or "testing" status cannot be cancelled and require lab notification. A cancellation reason is recommended for audit purposes. Use this when an order was submitted in error, the patient refused testing, or clinical circumstances have changed. Cancel a pending laboratory order
create_patient_record
Required fields: first name, last name, date of birth, and gender. Optional: address, phone, email, MRN (Medical Record Number), and insurance information. Use this to register a new patient before submitting lab orders. Returns the patient ID for use in subsequent order submissions. Create a new patient record in the Health Gorilla system
get_lab_results
Returns structured data suitable for EHR integration or clinical review. Results include timestamp of completion, pathologist sign-off (if applicable), and any critical value notifications. Use this to review patient results, identify abnormal values, or populate EHR records. Retrieve detailed laboratory results for a specific completed order
get_order_status
Status values include: "received", "in_progress", "collected", "testing", "completed", "cancelled". Returns order details, specimen collection status, lab processing information, and estimated completion time. Use this to track order progress, update patients on result timelines, or verify completion status. Check the current status of a submitted laboratory order
get_patient_demographics
Returns name, DOB, gender, contact information, MRN, and registration date. Use this to verify patient identity before order submission or to review patient registration details. Get demographic information for a registered patient
get_provider_details
Use this to verify provider credentials, obtain contact information for referrals, or confirm network participation before ordering tests. Get detailed information about a specific healthcare provider
list_orders
Optional filters: status (e.g., "pending", "completed", "cancelled") and patient_id. Each order includes order ID, patient name, test names, status, order date, and performing lab. Use this to review recent orders, track pending work, or audit ordering patterns. List laboratory orders with optional filtering by status or patient
list_patient_results
Includes test names, values, dates, and order references. Useful for trend analysis and longitudinal patient monitoring (e.g., tracking HbA1c over time, monitoring lipid panels). Use this for chronic disease management, preventive care follow-up, or comprehensive patient history review. List all laboratory results for a specific patient across all orders
match_patient
Returns match score and potential matches. Use this before creating new orders to avoid duplicate patient records and ensure results are attributed to the correct patient. Critical for data integrity in healthcare systems. Match a patient against existing records in the Health Gorilla network
search_lab_tests
Returns test names, LOINC codes, categories (chemistry, hematology, microbiology, etc.), turnaround times, and performing laboratory information. Use this to find the correct test codes (LOINC/CPT) before submitting orders, explore available diagnostic options, or verify test availability. Optional query parameter accepts free-text search. Optional category parameter filters by test type. Search the Health Gorilla lab test catalog by name, LOINC code, or category
search_providers
Results include provider name, specialty, NPI number, location, and contact information. Use this to find ordering providers, verify network participation, or locate specialists in a specific area. Optional filters: specialty (e.g., "Internal Medicine", "Cardiology") and location. Search for healthcare providers in the Health Gorilla network
submit_lab_order
The order includes patient demographics, ordering provider information, requested tests (LOINC/CPT codes), clinical indication/diagnosis (ICD-10 codes), and specimen collection details. Returns an order ID for tracking status and retrieving results. Use this to place lab orders electronically without manual paperwork. Supported test types include chemistry panels, CBC, metabolic panels, infectious disease testing, genetic testing, and radiology orders. The order is routed to the appropriate performing laboratory (Quest, LabCorp, etc.). Submit a new laboratory or radiology order through the Health Gorilla diagnostic network
Troubleshooting Health Gorilla MCP Server with OpenAI Agents SDK
Common issues when connecting Health Gorilla to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Health Gorilla + OpenAI Agents SDK FAQ
Common questions about integrating Health Gorilla MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Health Gorilla with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Health Gorilla to OpenAI Agents SDK
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.