How to Use the Crisp MCP in LangChain

Q: How do I initialize the Crisp MCP Server in LangChain?

Install langchain-mcp-adapters and initialize the MCP client with your Vinkius Crisp URL. This exposes tools like getvisitorprofile directly to your LangChain agent.

Chain Crisp support actions like `send_message` with LangChain's stateful LangGraph agents to run automated chat workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crisp MCP to LangChain

Create your Vinkius account to connect Crisp 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 Crisp with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-respond to support threads via LangChain

The `send_message` tool lets your LangChain agent write replies directly back to active Crisp chats. Your chains evaluate incoming customer questions from `get_messages` and post responses without manual steps. By linking these Crisp actions, your LangGraph pipeline reads the conversation history before writing back. LangSmith traces the exact token usage and payload for every `send_message` execution.

Context-aware routing using visitor profiles

The `get_visitor_profile` tool fetches contact details and metadata from Crisp to feed your LangChain prompt templates. Your agent inspects this profile to route high-value leads to specific support queues. You build these routing decisions directly into your LangGraph state transitions using the profile data. This ensures your LangChain pipeline tailors its answers based on the visitor's Crisp metadata.

Bulk analysis of active chat queues

The `list_conversations` tool pulls your active Crisp inbox queue directly into a LangChain document loader. Your chains scan this list to group similar support tickets together. Combining this with `get_conversation` allows the LangChain agent to extract specific pain points from multiple Crisp users at once. You get a clear picture of trending bugs inside your LangSmith dashboard.

Setup guide

Set up Crisp 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 Crisp 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({
    "crisp-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 Crisp 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 Crisp. 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 Crisp 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 Crisp MCP in LangChain

Install `langchain-mcp-adapters` and initialize the MCP client with your Vinkius Crisp URL. This exposes tools like `get_visitor_profile` directly to your LangChain agent.

Yes, you can build a LangGraph chain that takes the output of `get_messages` and passes it to `send_message`. This lets the LangChain agent read and reply to Crisp threads.

Use LangSmith tracing to inspect the exact input payloads passed to `get_visitor_profile`. You will see the raw JSON response and latency for every Crisp API call.

Yes, the multi-server client aggregates your Crisp endpoint alongside databases or vector stores. Your LangChain agent dynamically decides whether to query Crisp profiles or local databases.

Yes, Vinkius runs the Crisp MCP Server inside an isolated, zero-trust sandbox. Your customer profiles and conversation histories are never stored or exposed during LangChain executions.

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