How to Use the Knack MCP in LangChain

Q: How do I let my LangChain agent create new records in Knack?

Give your agent the createrecord tool. The agent should first call listobjectfields to learn the required field keys, then construct the JSON payload and execute the write.

Q: Can a LangChain agent search for specific data in my Knack database?

Yes. The searchrecords tool is designed for this exact task. Your agent can formulate the filter JSON based on a user's request and get back a list of matching records from Knack.

Q: What's the best way to explore my Knack schema with a LangChain agent?

Start with listobjects to get all your tables. For a specific table, chain that with getobjectschema and listobjectfields. These three calls in sequence give your agent a complete map of the database.

Q: What happens if I try to delete a record?

The deleterecord tool permanently removes the record from your Knack object. That action is irreversible, so make sure your agent's logic includes a confirmation step or human-in-the-loop check before calling it.

Build multi-step LangChain agents that read, write, and manage your Knack database.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knack MCP to LangChain

Create your Vinkius account to connect Knack 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 Knack with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map and Modify Your Database

Give your agent the tools to understand your database before it acts. A LangChain agent can start with `list_objects` to see all your tables, then run `list_object_fields` to get the exact structure of a specific one. This is the discovery step—no data gets touched until the agent has a map. Once it has the schema, the agent can get to work. It can `search_records` to find a specific entry based on complex criteria, then pipe that record's ID directly into `update_record` to change a field. You're not just calling tools; you're building an autonomous chain that finds and fixes data.

Automate Record Creation with LangChain

This is more than just inserting a row. Your agent can pull unstructured data from an email, a document, or another API call. It then uses `get_object_schema` on your Knack database to check which fields are required for a new record. The agent formats the data correctly and makes the final `create_record` call. Because it's a LangChain agent, you get full visibility into the entire chain of thought in LangSmith. You can see exactly how it parsed the source data and why it chose to create the record.

Run Dynamic Audits and Reports

Build reporting agents that react to your data in real time. An agent can kick off a workflow by calling `list_account_applications` to get a high-level view of your Knack account. From there, it can loop through key objects and use `list_records` to pull the raw data for a summary. If it finds an anomaly or an entry that needs a closer look, the chain can automatically trigger a `get_record` call to pull the full details for that single item. The final step could be another tool call that sends the compiled report to a Slack channel, completing the automated pipeline.

Setup guide

Set up Knack 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 Knack 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({
    "knack-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 Knack 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 Knack. 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 Knack 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 Knack MCP in LangChain

Give your agent the `create_record` tool. The agent should first call `list_object_fields` to learn the required field keys, then construct the JSON payload and execute the write.

Yes. The `search_records` tool is designed for this exact task. Your agent can formulate the filter JSON based on a user's request and get back a list of matching records from Knack.

Start with `list_objects` to get all your tables. For a specific table, chain that with `get_object_schema` and `list_object_fields`. These three calls in sequence give your agent a complete map of the database.

The `delete_record` tool permanently removes the record from your Knack object. That action is irreversible, so make sure your agent's logic includes a confirmation step or human-in-the-loop check before calling it.

Your agent only interacts with your Knack records and object schemas through the tools you explicitly grant it. Vinkius processes these tool calls in an ephemeral, zero-trust sandbox. Your Knack credentials are never exposed to the agent.

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