How to Use the Sensible MCP in LlamaIndex

Q: How can I use LlamaIndex to query Sensible extraction results?

After you run an extraction with a tool like extractsync, take the returned JSON output and load it into a LlamaIndex Document object. Once indexed, you can query the structured data using any LlamaIndex query engine.

Q: What's the difference between using extractsync and extractfromurl with Sensible in a LlamaIndex app?

Use extractsync for quick, interactive queries where your agent needs an immediate result to continue its task. Use extractfromurl for larger files or batch jobs where the agent can submit the job and check for the indexed result later.

Q: Can I filter which Sensible tools my LlamaIndex agent can access?

Yes. When you initialize the McpToolSpec, you can pass an allowedtools list containing the names of the only tools you want the agent to use. This is a good way to restrict agents to read-only operations.

Index document extractions to build smarter RAG applications with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sensible MCP to LlamaIndex

Create your Vinkius account to connect Sensible to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sensible with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Turn Extraction History into a Knowledge Base

This MCP server lets your agent query the history of its own work. Use `list_extractions` to pull past parsing jobs and then index the structured results with LlamaIndex. Now you can ask your application questions like, "Show me all failed extractions for 'Invoice' documents last week." Your RAG application's context isn't just static text; it's a live record of your document processing activity. You can even index configuration details using `list_configurations` and `get_configuration_version` to track how your parsing rules have changed over time.

Build a Document Intelligence Index with an MCP Server

Go beyond simple text extraction by creating a queryable index of your actual documents. Your agent can use `generate_upload_url` to send a document to Sensible, run `extract_from_url`, and then index the structured JSON output. This gives your LlamaIndex agent deep, structured knowledge about each file. Combine this with tools like `get_extraction_statistics` to add performance metrics to your knowledge base. Your agent can now answer questions about extraction accuracy and field coverage by querying its own index, grounding its responses in real operational data.

Manage Reference Data for Better RAG

Improve your RAG system's accuracy by managing 'golden' reference documents. Your LlamaIndex agent can use `create_golden` to upload a perfect example of a document, then use `extract_text_from_golden` to get a baseline for what correct extraction looks like. This reference data can be indexed, giving your agent a ground-truth source to compare against new, unseen documents. It's a way to build a feedback loop where your agent learns from curated examples, making your document Q&A much more reliable.

Setup guide

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

After you run an extraction with a tool like `extract_sync`, take the returned JSON output and load it into a LlamaIndex `Document` object. Once indexed, you can query the structured data using any LlamaIndex query engine.

Yes. You can set up a pipeline where a new document triggers an `extract_from_url` call. The resulting structured data is then immediately indexed into your vector store, making it available for queries instantly.

Use `extract_sync` for quick, interactive queries where your agent needs an immediate result to continue its task. Use `extract_from_url` for larger files or batch jobs where the agent can submit the job and check for the indexed result later.

Yes. When you initialize the `McpToolSpec`, you can pass an `allowed_tools` list containing the names of the only tools you want the agent to use. This is a good way to restrict agents to read-only operations.

Sensible receives your documents—like PDFs or scans—to perform data extraction, and the processing is isolated. When you use LlamaIndex, the extracted data is returned to your agent, which you then control. It's your responsibility to secure the vector index where you store the extracted document content.

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