How to Use the 7shifts MCP in LlamaIndex

Q: How do I load 7shifts tools into LlamaIndex?

Grab the llama-index-tools-mcp package. Set up a BasicMCPClient, wrap it in McpToolSpec, and await the totoollistasync() method to feed your FunctionAgent.

Q: Can LlamaIndex query 7shifts employee roles directly?

They can. The agent executes listroles or listdepartments when a user asks about organizational structure. It grounds its response in the live data pulled from Vinkius.

Q: How do I filter which 7shifts tools LlamaIndex can access?

Use the allowedtools parameter when setting up your tool spec. You might restrict an agent to only getaccountinfo and listlocations if it doesn't need scheduling access.

Turn your restaurant schedules and staff rosters into a searchable LlamaIndex knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 7shifts MCP to LlamaIndex

Create your Vinkius account to connect 7shifts 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 7shifts with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorize Your Workforce Data

Querying a REST API directly is slow and rigid. LlamaIndex pulls your 7shifts data through the MCP protocol and embeds it right into your vector store. You run `list_employees` and `list_roles`, and those raw JSON outputs become semantically searchable documents. Managers can ask plain-English questions about the team structure. The system retrieves the exact profile details from the index instead of guessing or making up answers about who works in which department.

Ground RAG Apps with 7shifts MCP Server

Static documents go stale fast in a restaurant environment. Your LlamaIndex application stays current by fetching live data via `list_schedules` and `list_shifts` right before answering a query. If a server asks about their upcoming weekend shifts, the FunctionAgent triggers the tool to get the ground truth. It merges that live API response with any training manuals you already indexed.

Index Time Punch History

Labor cost analysis requires looking at historical patterns. You can configure a data ingestion pipeline that periodically runs `list_time_punches` and adds the records to your knowledge base. This lets you run complex queries about late clock-ins or overtime trends. The agent searches the embedded time entries and returns hard numbers backed by the actual 7shifts logs.

Setup guide

Set up 7shifts 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 7shifts 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 7shifts tools.",
)
response = await agent.run("List recent 7shifts 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 7shifts. 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 7shifts 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 7shifts MCP in LlamaIndex

Grab the `llama-index-tools-mcp` package. Set up a `BasicMCPClient`, wrap it in `McpToolSpec`, and await the `to_tool_list_async()` method to feed your FunctionAgent.

They can. The agent executes `list_roles` or `list_departments` when a user asks about organizational structure. It grounds its response in the live data pulled from Vinkius.

Use the `allowed_tools` parameter when setting up your tool spec. You might restrict an agent to only `get_account_info` and `list_locations` if it doesn't need scheduling access.

That depends on your vector store setup. The MCP connection fetches fresh results via `list_schedules`, which you can choose to index permanently or treat as ephemeral context.

Vinkius handles the authorization layer outside your code. When LlamaIndex retrieves sensitive shift details or profile information, the transaction happens inside a zero-trust environment requiring only a single endpoint token.

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