How to Use the AskNicely MCP in LangChain

Q: Can LangChain trigger AskNicely surveys automatically?

Yes. Your agent decides when to call triggersurvey based on the prompt instructions. It handles the contact addition and sends the request immediately.

Q: Does LangSmith track AskNicely tool calls?

Every invocation of listresponses or getstatistics shows up in your traces. You see the exact token usage and latency for each API interaction.

Build multi-step ReAct agents that chain AskNicely survey triggers with LangChain observability via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AskNicely MCP to LangChain

Create your Vinkius account to connect AskNicely 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 AskNicely with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect AskNicely to LangChain Agents

Your ReAct agent needs real customer sentiment before making decisions. The AskNicely MCP Server lets your pipeline pull aggregate NPS data directly into its context window. You build chains that start by calling `get_statistics` to read current scores. The agent evaluates those metrics against historical baselines. If the score drops below a threshold, the chain automatically invokes `list_responses` to find the exact negative feedback causing the dip. Everything gets logged in LangSmith for full tracing.

Trigger Surveys Mid-Pipeline

Stop treating customer feedback as a separate workflow. Your LangGraph nodes can actively reach out to users right after a specific interaction. The `trigger_survey` tool takes a contact and fires off an immediate NPS request. Output from that tool call flows directly into the next step of your chain. You could have a downstream node wait for the response, then summarize the sentiment. It turns passive data collection into an active, programmable loop.

Manage Audience Context

Good agents need to know who they are talking to. Fetching the current audience list happens through the `list_contacts` endpoint. Your chain uses this to verify a user exists before attempting any outreach. Missing contacts get flagged instantly. The pipeline calls `get_account_check` to ensure the AskNicely connection remains active, preventing silent failures during massive batch operations.

Setup guide

Set up AskNicely 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 AskNicely 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({
    "asknicely-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 AskNicely 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 AskNicely. 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 AskNicely 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 AskNicely MCP in LangChain

Install langchain-mcp-adapters. Use MultiServerMCPClient pointing to your Vinkius endpoint, then pass the fetched tools into your create_agent setup.

Yes. Your agent decides when to call trigger_survey based on the prompt instructions. It handles the contact addition and sends the request immediately.

Every invocation of list_responses or get_statistics shows up in your traces. You see the exact token usage and latency for each API interaction.

The agent receives an error from the tool call. You can design your chain to catch this and run get_account_check to debug the connection state.

Vinkius runs this integration in an ephemeral V8 Isolate. When your agent pulls emails via list_contacts or reads survey text, the data flows directly to your client. We never store your NPS responses.

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