How to Use the AlgoDocs MCP in LlamaIndex

Q: How do I add AlgoDocs tools to LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient pointing to the Vinkius endpoint. Wrap it in an McpToolSpec and pass the asynchronous tool list to your FunctionAgent.

Q: Can LlamaIndex search the text AlgoDocs extracts?

Yes. Once the agent retrieves text via getdocumentdata, it chunks and embeds that content. Your users can then run semantic searches against the parsed document data.

Q: How does the LlamaIndex agent know when an AlgoDocs file is ready?

You give the agent access to getdocumentstatus. It checks the processing state and only attempts to index the final text once the job completes.

Q: Can I monitor my API usage through RAG?

Your agent reads getapiusage and getmyaccount. If a user asks why a document failed to index, the system can check if you hit a billing limit.

Turn parsed PDFs into searchable knowledge bases using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AlgoDocs MCP to LlamaIndex

Create your Vinkius account to connect AlgoDocs 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 AlgoDocs with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index raw documents via MCP Server

Raw PDFs are useless until you extract the text. Your LlamaIndex application calls `upload_document_from_url` to ingest remote files, then waits for the extraction to finish. Instead of just reading the output, your agent grabs the text using `get_document_data` and immediately embeds it. Those chunks go straight into your vector store, making yesterday's static invoices instantly queryable.

Query across historical extractions

Sometimes you need context on what the system processed last week. This MCP Server integration lets a FunctionAgent run `list_recent_documents` to pull metadata on recently parsed files. It then uses `list_folders` to figure out where specific extractions live. By indexing this metadata alongside the actual text, your RAG setup answers questions about both the content and the processing pipeline itself.

Dynamic extractor routing

Different documents require different parsing logic. Your RAG app queries `list_extractors` to understand which AI models are currently configured in your account. When a user asks a question that requires specific invoice data, the agent knows exactly which extractor handled that format. It pulls the right batch data via `list_extractor_data` to ground its response in actual API results.

Setup guide

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

Install `llama-index-tools-mcp` and set up a `BasicMCPClient` pointing to the Vinkius endpoint. Wrap it in an `McpToolSpec` and pass the asynchronous tool list to your `FunctionAgent`.

Yes. Once the agent retrieves text via `get_document_data`, it chunks and embeds that content. Your users can then run semantic searches against the parsed document data.

You give the agent access to `get_document_status`. It checks the processing state and only attempts to index the final text once the job completes.

Your agent reads `get_api_usage` and `get_my_account`. If a user asks why a document failed to index, the system can check if you hit a billing limit.

Vinkius isolates every request inside an ephemeral sandbox. Your LlamaIndex application fetches parsed invoices and Word documents, but zero trust architecture ensures no residual text remains on the server after the connection closes.

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