How to Use the Planhat MCP in LangChain

Q: Can I combine Planhat data with vector databases in LangChain?

Absolutely. You can fetch raw company details with getplanhatcompany and feed that text directly into your LangChain document loaders. This lets you run semantic searches over your Planhat customer profiles alongside internal docs.

Run multi-step customer success workflows in LangChain by chaining live Planhat MCP tools directly into your agentic loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Planhat MCP to LangChain

Create your Vinkius account to connect Planhat to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Planhat with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Planhat diagnostics inside LangChain agents

`get_planhat_company` retrieves company health metrics so your LangChain agent can immediately decide if an account needs urgent intervention. The tool feeds raw customer status to the next link in your chain, letting you automate complex triage without manual lookups. You don't have to write custom glue code to move data between steps. LangChain passes the output of `list_planhat_companies` straight to your custom notification tools, giving you a live alert pipeline that triggers whenever an enterprise account drops in health.

Trace Planhat MCP Server execution with LangSmith

`list_planhat_conversations` retrieves customer chat histories and exposes them to LangChain with full execution visibility. LangSmith traces every single call, showing you the exact customer notes and conversation logs your agent pulled during its run. This tracing stops silent failures in their tracks. You see the latency of `list_planhat_tasks` and the exact tokens consumed when your LangChain agent compiles action items for your customer success team.

Coordinate cross-platform tasks in a single chain

`list_planhat_projects` lets your LangChain agent map out onboarding milestones and link them directly to external database updates in a single execution loop. You combine Planhat tracking with your other API chains to keep customer data synchronized across your entire stack. By feeding the output of `list_planhat_licenses` into a multi-server LangChain MCP setup, your agent can verify customer seats and automatically update external billing systems. It turns manual verification into a single, predictable run.

Setup guide

Set up Planhat 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 Planhat 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({
    "planhat-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 Planhat 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 Planhat. 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 Planhat 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 Planhat MCP in LangChain

You handle rate limits by setting up LangChain retry configurations or managing rate-limiting middleware directly on your client. The MCP Server passes Planhat's standard API responses directly, letting your chain catch 429 status codes and pause execution.

Yes, you can build a chain where the agent reads recent updates using `list_planhat_notes` and then calls `list_planhat_tasks` to check for outstanding items. Your LangChain agent then uses this context to decide if it needs to prompt a human for task creation.

LangChain uses LangSmith to trace the exact input parameters and JSON outputs of `list_planhat_conversations`. You see the raw text of the customer logs directly in your tracing dashboard, making it easy to debug agent decisions.

Absolutely. You can fetch raw company details with `get_planhat_company` and feed that text directly into your LangChain document loaders. This lets you run semantic searches over your Planhat customer profiles alongside internal docs.

The server runs inside a secure, sandboxed V8 isolate on Vinkius, meaning your Planhat customer notes, conversation logs, and license details are never cached or exposed. Your API token is kept in memory during the session and is completely wiped the moment the execution ends.

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