How to Use the Daftra MCP in LlamaIndex

Q: How do I configure Daftra with LlamaIndex?

Grab the llama-index-tools-mcp package from pip. Set up a BasicMCPClient with your Vinkius URL, wrap it in McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can LlamaIndex update Daftra records?

The agent can execute mutations if you allow it. Calling createclient will write a new contact to the database. This MCP integration allows restrictions by using the allowedtools filter during initialization.

Q: How do I get site-wide settings?

The getsitemetadata tool returns organizational settings and site identifiers. Your agent reads this to understand the context of the account before answering user queries.

Index your ERP data. Connect Daftra to LlamaIndex to query live invoices, estimates, and client histories.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daftra MCP to LlamaIndex

Create your Vinkius account to connect Daftra 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 Daftra with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live ERP data via MCP Server

`get_client_details` pulls granular CRM data, including outstanding balances and contact history. LlamaIndex takes this raw output and converts it into document nodes. These nodes go straight into your vector store for semantic search. You stop relying on static exports. The query engine hits the API in real-time, embedding the exact financial snapshot of that account. Users get answers grounded in live database state.

Search sales invoices semantically

`list_invoices` returns arrays of invoice numbers, totals, and payment statuses. Your application indexes these arrays alongside unstructured documents like email threads. When a user asks about a specific project, the system retrieves both the communication and the billing reality. We designed this for deep cross-referencing. Fetching `get_invoice_details` gives the system line-item granularity. The LLM synthesis step merges tax details from the API with contract terms from your PDF index.

Build quoting engines

`list_estimates` extracts all price quotes from your sales pipeline. You can pipe this data into a router query engine. The engine decides whether to check historical quotes or search through standard pricing documents. Inventory plays a crucial role here too. By calling `list_inventory_products`, the agent knows exactly what services exist right now. It generates responses based on actual available SKUs rather than hallucinated product names.

Setup guide

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

Grab the `llama-index-tools-mcp` package from pip. Set up a `BasicMCPClient` with your Vinkius URL, wrap it in `McpToolSpec`, and pass the async tool list to your `FunctionAgent`.

The agent can execute mutations if you allow it. Calling `create_client` will write a new contact to the database. This MCP integration allows restrictions by using the `allowed_tools` filter during initialization.

Yes, it works with any supported backend. The tools just return raw text and JSON, which the framework embeds into whichever database you configured.

The `get_site_metadata` tool returns organizational settings and site identifiers. Your agent reads this to understand the context of the account before answering user queries.

We use a zero-trust architecture. When the agent fetches business costs via `list_expenses`, the Vinkius container executes the request and immediately terminates. We never cache your raw financial arrays.

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