How to Use the Float MCP in LangChain

Q: How do I connect LangChain to the Float MCP Server?

Run pip install langchain-mcp-adapters langgraph first. Initialize the MultiServerMCPClient with the Vinkius HTTP endpoint, then pass the tools from client.gettools() directly into your agent constructor.

Q: Can a LangChain agent resolve scheduling conflicts in Float?

Yes, by chaining listallocations and listtimeoffs to find open slots. The agent evaluates the returned datasets sequentially and uses createallocation to write the new schedule back to your team calendar.

Q: How do I monitor Float tool execution latency in LangChain?

LangSmith traces each call to tools like getloggedtime automatically. You get a visual breakdown of execution times, token costs, and raw payload data for all scheduling queries.

Build LangChain chains that schedule tasks and audit team hours directly through the Float 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 Float MCP to LangChain

Create your Vinkius account to connect Float 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 Float with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step scheduling chains

The Float MCP Server exposes `list_people` and `list_time_offs` to let your LangChain ReAct agent analyze team availability before booking work. Your agent checks who is free, filters out anyone on vacation, and then triggers `create_allocation` to assign tasks without human intervention. Using LangSmith, you trace each step of this allocation chain to see exactly how the agent decided on a specific team member. If an allocation fails, the trace reveals whether the bottleneck was a rate limit or a scheduling conflict.

Automated project auditing with LangChain

This integration pairs `get_logged_time` with `list_projects` so your LangChain chains can flag budget overruns on active projects. The agent pulls the actual hours logged against a project, compares it to the allocated hours, and outputs a clean markdown report. You can feed this report directly into a database or Slack integration using LangChain's massive library of 500+ ecosystem integrations. It turns raw scheduling metrics into instant, actionable alerts.

Multi-server coordination

Combining the Float MCP Server with other endpoints is straightforward when using LangChain's `MultiServerMCPClient` to fetch client profiles via `list_clients`. By maintaining stateless execution, your LangChain system handles high-volume Float scheduling queries without memory leaks. If your LangChain agent needs session persistence across multiple Float scheduling steps, simply spin up a client session. This keeps your context isolated and clean.

Setup guide

Set up Float 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 Float 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({
    "float-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 Float 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 Float. 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 Float 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 Float MCP in LangChain

Run `pip install langchain-mcp-adapters langgraph` first. Initialize the `MultiServerMCPClient` with the Vinkius HTTP endpoint, then pass the tools from `client.get_tools()` directly into your agent constructor.

Yes, by chaining `list_allocations` and `list_time_offs` to find open slots. The agent evaluates the returned datasets sequentially and uses `create_allocation` to write the new schedule back to your team calendar.

LangSmith traces each call to tools like `get_logged_time` automatically. You get a visual breakdown of execution times, token costs, and raw payload data for all scheduling queries.

LangChain handles rate limits by bubbling up the error through the tool call step. You can wrap your chain in a retry loop to pause and retry when `list_projects` or other tools return rate limit codes.

Vinkius runs the server in a zero-trust, sandboxed V8 Isolate. Your team's historical records from `get_logged_time` and allocation details are processed ephemerally, ensuring no scheduling data persists on the proxy.

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