How to Use the Gingr MCP in LangChain

Q: How do I handle Gingr connection timeouts in my LangChain agent?

Use verifyapiconnection as your first step in the LangChain sequence. If the connection fails, write a custom error handler in LangChain to retry the connection before running listactivecheckins on your Gingr database.

Q: How does LangChain parse custom owner fields from Gingr?

The LangChain agent calls searchownercustomfields and receives raw JSON containing your custom database keys. LangChain then parses this structured payload to extract specific details like gate codes or premium service preferences for that pet owner.

Q: How do I pass Gingr owner contact details to other APIs in the same LangChain chain?

You run getpetownerdetails to pull the profile data into your LangChain workflow. LangChain then passes that output directly to your next node, whether that is an email sender or an SMS tool.

Run multi-step pet boarding workflows by chaining Gingr API calls using this LangChain MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gingr MCP to LangChain

Create your Vinkius account to connect Gingr 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 Gingr with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step pet intake chains in LangChain.

`list_active_checkins` pulls your kennel's active facility roster directly into your LangChain agent's running execution context. From there, the LangChain agent chains a second call to `get_pet_owner_details` to verify emergency contacts for those checked-in pets. You track every single Gingr tool execution, latency spike, and token count inside LangSmith to debug your boarding workflows. If a chain fails to find a pet profile, the LangChain agent automatically falls back to `find_owner_by_phone` to resolve the boarding record discrepancy.

Validate Gingr connections using this LangChain MCP Server.

`verify_api_connection` acts as the initial guardrail in your LangChain initialization sequence before accessing pet records. The LangChain agent runs this check first to ensure your Gingr credentials haven't expired before starting the daily run. This programmatic verification prevents LangChain from executing complex boarding queries on a broken endpoint. By halting the chain early, you avoid wasted LLM tokens when the Gingr API is down.

Trace custom pet field queries with LangChain.

`search_pet_custom_fields` scans your boarding database for specific medical alerts and feeds that raw data directly into your LangChain prompt templates. When your LangChain agent processes a raw text query from an owner, it maps the intent to this tool to extract custom pet notes. This setup guarantees that custom notes about aggressive behavior flow directly into your LangChain safety chains. You get a clear, traceable path in LangSmith from the raw Gingr database field to the final agent response.

Setup guide

Set up Gingr 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 Gingr 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({
    "gingr-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 Gingr 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 Gingr. 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 Gingr 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 Gingr MCP in LangChain

Use `verify_api_connection` as your first step in the LangChain sequence. If the connection fails, write a custom error handler in LangChain to retry the connection before running `list_active_checkins` on your Gingr database.

No, this MCP Server only supports read-only operations like `get_digital_whiteboard` and `list_active_checkins` within your LangChain agent. Your LangChain agent can read the current state of the kennel but cannot write changes back to your Gingr instance.

The LangChain agent calls `search_owner_custom_fields` and receives raw JSON containing your custom database keys. LangChain then parses this structured payload to extract specific details like gate codes or premium service preferences for that pet owner.

You run `get_pet_owner_details` to pull the profile data into your LangChain workflow. LangChain then passes that output directly to your next node, whether that is an email sender or an SMS tool.

Your pet owner details and reservation schedules remain completely local to your infrastructure while running LangChain. Vinkius runs the MCP Server in an isolated sandbox, meaning the data goes straight to your LangChain agent without being stored on our 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