How do I find the Object Key for a specific table?

Use the `list_objects` tool. It will return all data objects in your application along with their names and unique keys (e.g., `object_1`). Use these keys for all subsequent record operations.

Can I search records using multiple conditions?

Yes. Use the `search_records` tool and provide a JSON array of filter objects. For example: `[{"field":"field_1", "operator":"is", "value":"active"}, {"field":"field_2", "operator":"contains", "value":"premium"}]`.

How do I know which fields to use when creating a record?

Use the `list_object_fields` tool with the target `object_key`. It will list all fields, their types, and their keys (e.g., `field_1`), which you must use as property names in your data JSON.

Knack MCP Server for LangChain 10 tools — connect in under 2 minutes

Name: Knack
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 10 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Knack through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "knack": {
            "transport": "streamable_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,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Knack, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Knack MCP Server

Connect your Knack application to any AI agent and take full control of your no-code database through natural conversation.

LangChain's ecosystem of 500+ components combines seamlessly with Knack through native MCP adapters. Connect 10 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

What you can do

Database Schema Discovery — List all objects and fields to understand your data structure without leaving the chat
Record Management — Create, retrieve, update, and delete records in any object securely
Advanced Querying — Search for specific records using complex filters based on any field criteria
Data Auditing — Get detailed summaries of specific records to verify information or track changes
Bulk Operations — Effortlessly manage multiple records by providing structured data to your agent

The Knack MCP Server exposes 10 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Knack to LangChain via MCP

Follow these steps to integrate the Knack MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 10 tools from Knack via MCP

Why Use LangChain with the Knack MCP Server

LangChain provides unique advantages when paired with Knack through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents. combine Knack MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Knack queries for multi-turn workflows

Knack + LangChain Use Cases

Practical scenarios where LangChain combined with the Knack MCP Server delivers measurable value.

RAG with live data: combine Knack tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Knack, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Knack tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Knack tool call, measure latency, and optimize your agent's performance

Knack MCP Tools for LangChain (10)

These 10 tools become available when you connect Knack to LangChain via MCP:

create_record

You must provide the data as a JSON string where keys are the field keys (e.g., field_1). Ensure you have checked the object schema first to know which fields are required. Create a new record in a Knack object

delete_record

Use with caution as this action cannot be undone. Delete a record from a Knack object

get_object_schema

Returns metadata including the object name, key, and high-level structure. Use this to verify you are working with the correct database table. Get the schema of a specific Knack object

get_record

Requires both the object_key and the record_id. Use this for detailed auditing of a specific entry. Get a specific record by ID

list_account_applications

Use this to verify access or discover application IDs. List all applications in the account

list_object_fields

This is crucial for understanding the data types and identifying the field keys (field_1, field_2, etc.) needed for creating or updating records. List all fields for a specific Knack object

list_objects

This is the first step to understand the database structure and find the "Object Key" needed for record operations. List all objects in the Knack application

list_records

You must provide the object_key. Use this to browse the actual data stored in your database. List records for a specific Knack object

search_records

The filters must be provided as a JSON string following the Knack Filter format (e.g., "[{\"field\":\"field_1\", \"operator\":\"is\", \"value\":\"test\"}]"). Search for records using filters

update_record

Provide only the fields you wish to change in the JSON string data. This is a partial update. Update an existing record in a Knack object

Example Prompts for Knack in LangChain

Ready-to-use prompts you can give your LangChain agent to start working with Knack immediately.

"List all database objects in my Knack app"

"Find all premium customers in 'object_1'"

"Create a new customer in 'object_1' with name 'Sarah' and email 'sarah@example.com'"

Troubleshooting Knack MCP Server with LangChain

Common issues when connecting Knack to LangChain through the Vinkius, and how to resolve them.

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Knack + LangChain FAQ

Common questions about integrating Knack MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.