How to Use the Insightly MCP in LangChain

Q: How do I connect the Insightly MCP Server to LangChain?

Install the adapter using pip install langchain-mcp-adapters langgraph to begin. Then, initialize MultiServerMCPClient pointing to the Vinkius URL and pass the Insightly tools to your LangChain agent.

Build multi-step LangChain pipelines that inspect Insightly CRM data and trace every tool call with LangSmith.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Insightly MCP to LangChain

Create your Vinkius account to connect Insightly 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 Insightly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Insightly data into LangChain workflows

The `list_contacts` tool fetches your raw Insightly CRM directory and feeds it directly into your active LangChain run. Your LangChain agent takes that raw contact list and immediately passes it to the next link in the chain to match active Insightly opportunities. This setup avoids manual data transfers between Insightly and LangChain. You pass the results of `list_opportunities` straight into a custom LangChain prompt template, letting your agent draft personalized follow-ups based on real Insightly deal values.

Trace MCP Server calls using LangSmith

This MCP Server exposes tools like `list_projects` and `list_tasks` so your LangChain agent can inspect Insightly operational pipelines in real time. Every single API request is logged automatically in your LangSmith dashboard, showing you exact token usage and latency for each Insightly CRM query. You don't have to guess why a LangChain tool call failed or what payload it sent to Insightly. If `list_leads` returns an unexpected schema, you see the raw Insightly JSON payload in your LangSmith trace logs instantly.

Execute complex multi-step CRM reasoning

The `list_organisations` tool lets your LangChain agent look up company profiles before deciding which Insightly contacts to target. LangChain's ReAct framework evaluates the company size, then decides whether to invoke `get_contact` or pull the latest calendar events via `list_events` from Insightly. You get a self-correcting LangChain loop where the agent verifies the Insightly context at each step. Your LangChain agent queries `list_teams` to find the right account owner, then matches them with `list_users` to assign the next Insightly CRM task.

Setup guide

Set up Insightly 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 Insightly 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({
    "insightly-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 Insightly 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 Insightly. 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 Insightly 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 Insightly MCP in LangChain

Install the adapter using `pip install langchain-mcp-adapters langgraph` to begin. Then, initialize `MultiServerMCPClient` pointing to the Vinkius URL and pass the Insightly tools to your LangChain agent.

No, this integration only supports read operations for your LangChain workflows. Tools like `list_opportunities` and `get_contact` let your LangChain agent read Insightly CRM state, but you cannot create or edit records.

Your LangChain agent calls tools sequentially, which naturally throttles requests to the Insightly API. For high-volume tasks using `list_tasks`, you should implement a custom rate-limiting wrapper in your LangChain configuration.

Yes, you can mix these Insightly CRM tools with other LangChain integrations. Your LangChain agent can pull a lead with `list_leads` and immediately query a vector database in the same execution loop.

Your contacts, opportunities, and project data remain isolated within a secure V8 sandbox. Vinkius handles the Insightly API token authentication on an ephemeral basis, meaning your raw CRM credentials are never exposed to the LangChain LLM.

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