How to Use the Dext MCP in LlamaIndex

Q: How do I register the Dext MCP server in LlamaIndex?

Initialize BasicMCPClient with your server URL and wrap it in McpToolSpec. Then call the async tool list method and pass the output to your FunctionAgent.

Q: Can LlamaIndex search my historical Dext invoices?

Yes. The searchinboxbykeyword tool queries the API directly for specific records. You can combine this with semantic search across your local vector store for maximum coverage.

Q: Does the Dext MCP integration support multi-client accounting?

Your agent can call listaccountingclients to retrieve all associated accounts. It then indexes the data separately based on the client ID you provide.

Q: How do I check my Dext account limits through LlamaIndex?

Call the getaccountmetadata tool. It returns your current usage stats so your ingestion script knows when to pause.

Index your Dext receipts and supplier data into searchable LlamaIndex vector stores for instant RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dext MCP to LlamaIndex

Create your Vinkius account to connect Dext 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 Dext with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Dext receipts directly into LlamaIndex

The `list_inbox_items` tool pulls your processed receipts out of accounting purgatory and feeds them into your document ingestion pipeline. Your LlamaIndex agent takes this raw financial data and embeds it into a searchable vector store. Now you can ask your agent questions about past spending. Because it also calls `list_extracted_suppliers`, the index knows exactly which vendors you paid last quarter. You stop guessing and start querying actual ledger facts.

Build RAG pipelines for pending invoice audits

The `list_items_pending_review` tool isolates every transaction that needs human eyes. Your agent grabs this queue and cross-references it against historical spending patterns stored in your index. If a utility bill looks unusually high, the agent triggers `get_item_details` to extract the line items. It then retrieves last month's bill from the vector store and highlights the exact price difference for the auditor.

Ground financial queries in actual account metadata

The `list_accounting_categories` tool feeds your chart of accounts into the agent's context window. When a user asks how to classify a new software subscription, the AI answers using your actual tax codes instead of hallucinating generic advice. It maps these categories against `list_connected_bank_accounts` to show where the money actually left the building. This MCP Server turns a basic chat interface into a hyper-specific financial oracle.

Setup guide

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

Initialize `BasicMCPClient` with your server URL and wrap it in `McpToolSpec`. Then call the async tool list method and pass the output to your `FunctionAgent`.

Yes. The `search_inbox_by_keyword` tool queries the API directly for specific records. You can combine this with semantic search across your local vector store for maximum coverage.

Your agent can call `list_accounting_clients` to retrieve all associated accounts. It then indexes the data separately based on the client ID you provide.

Call the `get_account_metadata` tool. It returns your current usage stats so your ingestion script knows when to pause.

The framework embeds sensitive chart of accounts and supplier tax IDs directly into your local or private vector database. The MCP protocol isolates the API execution layer, meaning your raw Dext credentials are never exposed to the embedding model.

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