How to Use the Enrich CRM MCP in LangChain

Q: Can my LangChain agent avoid contacting existing customers using Enrich CRM?

Absolutely. After finding a prospect, have the agent call getaccountinfo. Your chain's logic can then decide whether to proceed or stop based on the account status returned by the tool.

Build autonomous sales research agents in LangChain that find and qualify leads without constant supervision.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Enrich CRM MCP to LangChain

Create your Vinkius account to connect Enrich 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 Enrich CRM with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Tool Calls for Lead Gen

Use LangChain to build agents that execute multi-step research on their own. Your agent can run `enrich_person` on a name, take the resulting company domain, and feed it directly into `enrich_company` to get firmographics. It's a logical sequence you design, but the agent runs. This isn't about one-off lookups. You're building a repeatable process where the agent decides the next best action. After finding a lead with `find_email`, it can check `get_account_info` to see if they're already a customer before logging a task in your CRM.

Full Observability with LangSmith

Every call your LangChain agent makes to this MCP Server is traced. LangSmith gives you a clear, step-by-step view of the inputs and outputs for `find_phone` or any other tool in the chain. You see exactly what data was passed and what came back. This makes debugging complex agent behavior simple. If a sequence fails, you can pinpoint whether it was a bad input to `enrich_company` or an unexpected empty result from `find_email`. No more guessing where your agent went wrong.

Build Once, Run Anywhere

Define your agent's logic one time. The Enrich CRM tools become standard LangChain tools once you load them using `client.get_tools()`. To your agent, it's just another tool in its kit. This means you can combine these CRM tools with hundreds of other LangChain integrations. Pull a list of domains from a Google Sheet, enrich them with `enrich_company`, and then save the results to a Postgres database—all inside a single, autonomous chain.

Setup guide

Set up Enrich 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 Enrich 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({
    "enrich-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 Enrich 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 Enrich 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 Enrich 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 Enrich CRM MCP in LangChain

You give the Enrich CRM tools to your LangChain agent. The agent can then decide on its own to call `enrich_person` on a prospect, then use that output to call `find_email`. It builds its own plan to get the data it needs.

Yes, every call is automatically traced in LangSmith if you have it configured. You'll see the full request and response for tools like `enrich_company` and `find_phone`, making it easy to debug your agent's reasoning.

Use a sequential chain or a ReAct agent. This lets your agent pass the output from one tool, like a company name from `enrich_person`, directly as the input to another tool like `enrich_company`.

Absolutely. After finding a prospect, have the agent call `get_account_info`. Your chain's logic can then decide whether to proceed or stop based on the account status returned by the tool.

The server only processes the specific data you send for enrichment, like a name or a domain. It doesn't store your contact lists. All connections are ephemeral and secured through your Vinkius token, so your raw CRM data is not exposed.

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