How to Use the Docamatic MCP in LlamaIndex

Q: How does Docamatic output integrate with LlamaIndex vector stores?

The MCP Server returns file paths for tools like generatepdffromhtml. Your LlamaIndex pipeline loads these files using standard PDF readers to index their contents directly.

Q: Can a LlamaIndex agent dynamically choose templates in Docamatic?

Yes. The agent calls listavailablebuiltintemplates to inspect the schema, then formats the user's data to fit generatepdffromtemplate before running the generation.

Q: Does the Docamatic MCP Server store any sensitive template JSON data?

All JSON payloads sent to generatepdffromtemplate are processed in memory and never written to permanent disk storage. Your client data is securely discarded as soon as the PDF is compiled.

Feed generated PDFs and HTML screenshots directly into your LlamaIndex vector stores for instant semantic search and RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docamatic MCP to LlamaIndex

Create your Vinkius account to connect Docamatic 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 Docamatic with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live document generation history for RAG

Your LlamaIndex agent can query the `list_generation_history` tool via the MCP connection to see what documents have been created, then pull those PDFs to index them. This lets your RAG pipeline search through actual historical outputs instead of relying on external databases. By feeding the output of `generate_pdf_from_html` directly into your document loaders, your index stays updated in real time. Your agent can answer user queries using the exact text rendered in your latest reports.

Query template structures using this MCP Server

Instead of hardcoding template schemas, let your LlamaIndex agent use `list_available_builtin_templates` to discover available layouts. The agent reads the template metadata, indexes the fields, and dynamically maps user queries to the correct JSON structure. When a user asks to generate a document, the agent populates `generate_pdf_from_template` with the extracted parameters. The resulting PDF is instantly ready for delivery or further indexing.

Capture and index web layouts as images

Use `take_web_screenshot` to capture visual states of web pages, then pass the image path to your multimodal indexing pipeline. Your LlamaIndex agent can analyze layout changes or visual regressions by comparing historical screenshots. If you need raw text extraction along with visual verification, the agent can run `generate_image_from_html` on specific components. This gives your agent both the visual proof and the structured content to index simultaneously.

Setup guide

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

The MCP Server returns file paths for tools like `generate_pdf_from_html`. Your LlamaIndex pipeline loads these files using standard PDF readers to index their contents directly.

Yes. The agent calls `list_available_builtin_templates` to inspect the schema, then formats the user's data to fit `generate_pdf_from_template` before running the generation.

Your agent identifies the files to combine from its index, then passes those paths to `merge_multiple_pdfs` to create a single unified document for the user.

No. You run the server locally or via our managed endpoint, then connect it using the LlamaIndex tool spec to expose the PDF tools directly.

All JSON payloads sent to `generate_pdf_from_template` are processed in memory and never written to permanent disk storage. Your client data is securely discarded as soon as the PDF is compiled.

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