How to Use the Freshsuccess MCP in LangChain

Q: How do I track the token cost of Freshsuccess tool calls in LangChain?

LangSmith automatically traces every tool call, including listcsaccounts and getuserhealth. You get a breakdown of prompt tokens, completion tokens, and execution latency for every customer success query.

Get real-time customer health metrics straight into your LangChain reasoning loops to stop churn before it starts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsuccess MCP to LangChain

Create your Vinkius account to connect Freshsuccess 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 Freshsuccess with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Account Health to Automated CS Tasks

This integration chains `get_account_health` and `list_cs_tasks` to build automated customer success triage loops. Your LangChain agent evaluates the health score of an account and immediately decides whether to generate a new follow-up task or update an existing one. By routing these MCP tool outputs directly into your agent's scratchpad, you bypass manual dashboard checks entirely. Every step of this multi-tool reasoning chain gets traced in LangSmith, showing you the exact latency and token usage for each decision.

Feed Freshsuccess Alerts into Multi-Step LangChain Agents

Your LangChain agent uses `list_cs_alerts` to scan for drop-offs in customer usage and trigger instant playbook runs. When an alert fires, the agent pulls the affected user list via `list_cs_users` to pinpoint who stopped logging in. You can feed these user lists into other LangChain integrations, like vector databases or external communication APIs. The agent coordinates these steps in a single run, keeping your customer success team ahead of critical account changes.

Run Custom Metric Pipelines with this MCP Server

This MCP Server exposes `post_metric_value` and `list_custom_metrics` to let your agent update telemetry data on the fly. You feed raw usage logs into your LangChain run, and the agent translates them into structured health updates. The agent checks the existing schema with `list_custom_metrics` before sending the new values. This keeps your Freshsuccess dashboard updated without manual data entry or custom cron jobs.

Setup guide

Set up Freshsuccess 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 Freshsuccess 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({
    "freshsuccess-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 Freshsuccess 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 Freshsuccess. 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 Freshsuccess 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 Freshsuccess MCP in LangChain

Your LangChain agent catches rate-limit errors from the server and retries the tool call using exponential backoff. The `check_api_status` tool lets the chain verify the connection before attempting heavy data pulls.

Yes. You can register this MCP server alongside SQL or vector database tools in your agent's toolkit. This lets the agent pull customer metadata with `get_account_health` and write it directly to your internal database.

LangSmith automatically traces every tool call, including `list_cs_accounts` and `get_user_health`. You get a breakdown of prompt tokens, completion tokens, and execution latency for every customer success query.

Install the MCP adapter package and initialize the client pointing to your Vinkius endpoint. From there, call the get tools helper to load `list_cs_tasks` and other operations into your agent's tool list.

Vinkius runs the MCP server in an isolated sandbox, keeping your customer health scores and account metadata safe. Your API keys are encrypted at rest, and the agent only accesses data through the specific endpoints like `get_account_health` that you authorize.

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