How to Use the Finch MCP in LlamaIndex

Q: How do I index Finch directory data into a LlamaIndex vector store?

You call listdirectory through the MCP Server to retrieve the employee list, then convert the JSON output into Document objects. LlamaIndex then chunks and embeds this directory data for semantic search.

Q: Can LlamaIndex query historical pay stubs retrieved via Finch?

Yes, you can fetch pay records using listpaystatements and store them in a queryable index. This lets your agent answer natural language questions about historical compensation trends.

Q: Does LlamaIndex support async tool execution with the Finch MCP Server?

Yes, you can use totoollistasync to load tools like getemployment and getindividual asynchronously. This keeps your indexing loops fast even when querying large payroll directories.

Q: How do I restrict which Finch tools LlamaIndex can access?

You use the allowedtools filter when initializing your McpToolSpec to restrict access. For example, you can expose listdirectory while blocking access to sensitive tools like listpaystatements.

Q: How does LlamaIndex protect employee SSNs and salaries fetched from Finch?

All sensitive HRIS data retrieved via getindividual is processed in memory within Vinkius's secure V8 sandbox. The raw payloads are encrypted in transit and never stored on external servers, keeping your payroll records private.

Index live HRIS and payroll data directly into LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finch MCP to LlamaIndex

Create your Vinkius account to connect Finch 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 Finch with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Semantic Search on Finch HR Data

LlamaIndex takes the output from `list_directory` or `get_employment` and indexes it directly into your vector database. This lets you run semantic queries over your actual workforce structure instead of relying on outdated CSV exports. Your agent uses the index to answer complex organizational questions, matching natural language queries to precise records returned by the MCP Server. This grounds your agent's answers in actual API data to prevent hallucinations.

Query Historical Pay Statements in LlamaIndex

By feeding `list_pay_statements` into a LlamaIndex document store, you make historical payroll records fully searchable. Your agent can compare past pay cycles or flag unusual shifts in compensation across different pay groups. You set this up by wrapping the MCP Server in `BasicMCPClient` and converting the tools using `McpToolSpec`. The resulting tool list gives your index-backed agent direct, real-time access to live payroll databases.

Verify Connection Status via this MCP Server

Before running expensive indexing pipelines, your LlamaIndex agent can run `introspect` and `get_me` to check permissions. This step ensures your agent has the right scopes to read sensitive fields like SSNs or salaries. If the connection lacks the required permissions, the agent can list supported integrations using `list_supported_providers` to find alternative routes. This self-correcting logic keeps your data ingestion pipelines running without manual intervention.

Setup guide

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

You call `list_directory` through the MCP Server to retrieve the employee list, then convert the JSON output into Document objects. LlamaIndex then chunks and embeds this directory data for semantic search.

Yes, you can fetch pay records using `list_pay_statements` and store them in a queryable index. This lets your agent answer natural language questions about historical compensation trends.

Yes, you can use `to_tool_list_async` to load tools like `get_employment` and `get_individual` asynchronously. This keeps your indexing loops fast even when querying large payroll directories.

You use the `allowed_tools` filter when initializing your `McpToolSpec` to restrict access. For example, you can expose `list_directory` while blocking access to sensitive tools like `list_pay_statements`.

All sensitive HRIS data retrieved via `get_individual` is processed in memory within Vinkius's secure V8 sandbox. The raw payloads are encrypted in transit and never stored on external servers, keeping your payroll records private.

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