How to Use the Float MCP in LlamaIndex

Q: How do I index Float allocation data in LlamaIndex?

Install llama-index-tools-mcp and initialize the BasicMCPClient. Load the tools using McpToolSpec and pass the output of listallocations to your vector indexer.

Q: Does LlamaIndex support filtering specific Float MCP Server tools?

You can use the allowedtools filter during setup to expose only specific tools like listprojects or listpeople. This prevents the agent from executing write operations like scheduling new tasks.

Q: How does this MCP Server prevent hallucinated timelines?

LlamaIndex forces the model to fetch real-time facts using listtimeoffs before answering schedule queries. This ensures all answers about team availability are grounded in active API data.

Index Float scheduling data into LlamaIndex vector stores to query team allocations using natural language.

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 LlamaIndex

Create your Vinkius account to connect Float to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic search over Float allocations

The Float MCP Server enables LlamaIndex to fetch raw resource data using `list_allocations` and index it directly into your vector database. Instead of manually parsing timelines, your LlamaIndex RAG pipeline lets you query who is working on what in Float using semantic search. This setup eliminates LlamaIndex hallucinations by grounding agent responses in live Float API data from tools like `get_person` and `list_projects`. Your LlamaIndex queries yield answers based on actual Float calendar facts rather than model guesses.

RAG-augmented resource planning

This integration uses `list_time_offs` and `list_departments` to combine internal team structures with external documents inside LlamaIndex. Your LlamaIndex agent can read a project proposal PDF, match the required skills against your Float departments, and draft allocations. By converting Float tool outputs into searchable LlamaIndex document nodes, you build a persistent knowledge base of team capacity. The agent references this LlamaIndex index to make smarter Float scheduling decisions over time.

Querying historical time logs in LlamaIndex

Accessing historical productivity metrics is fast when you connect LlamaIndex to the `get_logged_time` and `list_project_task_names` tools. The LlamaIndex framework indexes past Float logged hours alongside project milestones to analyze estimation accuracy. You configure this by setting up the LlamaIndex `BasicMCPClient` and converting the Float MCP Server tools into tool specs. Use the LlamaIndex `allowed_tools` filter to restrict the agent's access strictly to read-only Float time tracking tools.

Setup guide

Set up Float MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Float MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Float tools.",
)
response = await agent.run("List recent Float data")

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 LlamaIndex

Install `llama-index-tools-mcp` and initialize the `BasicMCPClient`. Load the tools using `McpToolSpec` and pass the output of `list_allocations` to your vector indexer.

Yes, if you do not restrict its permissions. The framework agent can call `create_allocation` to write new events directly based on the context it retrieves from your indexed documents.

You can use the `allowed_tools` filter during setup to expose only specific tools like `list_projects` or `list_people`. This prevents the agent from executing write operations like scheduling new tasks.

LlamaIndex forces the model to fetch real-time facts using `list_time_offs` before answering schedule queries. This ensures all answers about team availability are grounded in active API data.

Vinkius runs the Float MCP Server in a secure, ephemeral V8 Isolate sandbox. Your team names, email addresses, and details from `get_person` are transmitted via one-way tokens and never stored on our servers.

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