How to Use the Jiminny MCP in LangChain

Q: Can I use Jiminny and LangChain for real-time coaching?

Yes, you can build a chain that pulls gettranscript data after every call. The agent analyzes the text and returns actionable advice for the rep. It removes the delay between the call and the feedback.

Chain Jiminny data directly into your LangChain agents for automated sales performance analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jiminny MCP to LangChain

Create your Vinkius account to connect Jiminny 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 Jiminny with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated coaching pipelines

Connect call data to your reasoning chains. Use `get_call_stats` and `get_transcript` to feed raw conversation data directly into agentic workflows. Your agent parses these inputs to identify patterns without manual intervention. It triggers follow-up actions based on the insights it finds.

Trace every Jiminny tool call

Monitor your LangChain agent as it decides which tool to execute. Each `get_coaching_stats` or `get_action_items` call is logged for full visibility into your agent's decision logic. This visibility ensures you understand exactly why an agent reached a specific conclusion. You keep complete control over the reasoning loop.

Connect multiple MCP servers

Aggregate Jiminny data with other external services in a single LangChain pipeline. Combine `list_activities` with your CRM or database tools to create a unified view. The agent handles complex tasks by switching between these servers as needed. It builds a complete picture of your sales environment in one go.

Setup guide

Set up Jiminny 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 Jiminny 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({
    "jiminny-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 Jiminny 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 Jiminny. 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 Jiminny 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 Jiminny MCP in LangChain

Install the necessary adapters and initialize the client pointing to the server endpoint. You then fetch the tools and pass them into your agent constructor. This setup allows your agent to invoke Jiminny functions immediately.

Yes, you can build a chain that pulls `get_transcript` data after every call. The agent analyzes the text and returns actionable advice for the rep. It removes the delay between the call and the feedback.

It integrates natively with your existing tracing setup. Every call to the Jiminny tools will show up in your LangSmith dashboard. You can debug the inputs and outputs of every tool invocation.

The client is stateless by default. You can use a session object if you need to maintain context across multiple turns. Most users prefer the stateless approach for clean, predictable agent runs.

The server uses a single endpoint token for authentication. Your data is handled within the memory of your local agent process. No external service stores your call transcripts or coaching logs.

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