How to Use the Nimble CRM MCP in LangChain

Q: How do I make a LangChain agent find a contact and then add a note in Nimble CRM?

You'll build a chain where the agent first calls searchcontacts with a name. It then uses the returned contact ID as an input for the addnotetocontact tool. LangChain manages passing the output of one tool to the input of the next.

Q: Can my LangChain agent see all our sales pipelines in Nimble CRM?

Yes, the agent can call the listpipelines tool. This returns the names and stages of all configured deal pipelines in your Nimble CRM account, which you can use for reporting or decision-making in a chain.

Q: What's the best way to list all recent activities for a deal with LangChain and Nimble CRM?

First, use getdeal to fetch the deal's details. Then, your agent can use the listactivities tool, filtering the results for that specific deal. This gives you a clear history of tasks and events.

Q: Is it possible to build a summary agent that pulls data from multiple deals?

Absolutely. Your agent can call listdeals to get a set of deals, then loop through the results, calling getdeal for each one to gather more detail. It can then synthesize this information into a summary report.

Q: How is my Nimble CRM contact data protected when using LangChain?

Your data, including contact names and notes from getcontact or addnotetocontact, is sent directly to the Nimble CRM API through our managed MCP server. Vinkius handles authentication securely and the connection is encrypted. We don't store your contact data.

Build LangChain agents that manage your Nimble CRM, chaining contact lookups and deal updates into automated sales workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimble CRM MCP to LangChain

Create your Vinkius account to connect Nimble CRM 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 Nimble CRM with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Tool Calls to Move Deals

Create agents that follow a logical sales process. Your agent can `search_contacts` to find a person, `list_deals` associated with them, and then `add_note_to_contact` with the latest update. It's not just calling one tool; it's building a sequence. This lets your LangChain agent handle routine follow-ups. For example, it can check for stale deals with `list_deals` and then create a task for you by interacting with another service. You define the logic, the agent executes the steps.

Get CRM Data Inside Your LangChain Agent

Pull live data from Nimble CRM right into your agent's context. Use `get_contact` to fetch specific details or `get_deal` to see the current stage and value of an opportunity. No more stale data exports. Your agent uses this information to make better decisions. It can check `list_pipelines` to understand your sales stages before deciding what to do next. All tool inputs and outputs are visible in LangSmith, so you see exactly what's happening.

Context-Aware Note Taking

Stop switching tabs to update your CRM. Build a simple chain that takes a conversation summary and uses `add_note_to_contact` to log it against the correct person in Nimble. The agent can first use `get_me` to confirm its identity and permissions, then find the right person with `search_contacts`. This makes your note-taking faster and less error-prone. It's just part of the conversation.

Setup guide

Set up Nimble CRM 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 Nimble CRM 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({
    "nimble-crm-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 Nimble CRM 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 Nimble CRM. 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 Nimble CRM 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 Nimble CRM MCP in LangChain

You'll build a chain where the agent first calls `search_contacts` with a name. It then uses the returned contact ID as an input for the `add_note_to_contact` tool. LangChain manages passing the output of one tool to the input of the next.

Yes, the agent can call the `list_pipelines` tool. This returns the names and stages of all configured deal pipelines in your Nimble CRM account, which you can use for reporting or decision-making in a chain.

First, use `get_deal` to fetch the deal's details. Then, your agent can use the `list_activities` tool, filtering the results for that specific deal. This gives you a clear history of tasks and events.

Absolutely. Your agent can call `list_deals` to get a set of deals, then loop through the results, calling `get_deal` for each one to gather more detail. It can then synthesize this information into a summary report.

Your data, including contact names and notes from `get_contact` or `add_note_to_contact`, is sent directly to the Nimble CRM API through our managed MCP server. Vinkius handles authentication securely and the connection is encrypted. We don't store your contact data.

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