How to Use the Docdown MCP in LlamaIndex

Q: How can LlamaIndex search for Docdown templates?

Index the output of listdoctemplates into your vector store. Once indexed, your LlamaIndex agent can perform semantic searches to find the most relevant template for any user request.

Q: Can I query my Docdown document history in LlamaIndex?

Call listrecentlygenerateddocs to get a list of your latest files. Adding these to your LlamaIndex knowledge base allows you to chat with your history and find specific document IDs instantly.

Q: Does Docdown support schema inspection in LlamaIndex?

Yes, use gettemplatefieldschema to grab the data requirements for any template. LlamaIndex can store these schemas, helping the agent construct perfect payloads for the generation API.

Index your Docdown templates and generated files into LlamaIndex for semantic retrieval.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docdown MCP to LlamaIndex

Create your Vinkius account to connect Docdown 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 Docdown with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Docdown templates in LlamaIndex

Use `list_published_templates` to pull your current template library into your vector store. LlamaIndex then treats these templates as searchable knowledge. Your agent can find the right document structure by querying the index for specific business purposes. It stops guessing which template to use and starts matching based on semantic intent.

Ground AI answers in Docdown document history

Feed the results of `list_generated_documents` back into your RAG pipeline. This gives your agent a complete memory of what it has already created. It searches past documents to answer questions about previous output. You gain a searchable archive of your generated work without leaving the agent environment.

Verify document metadata with LlamaIndex tools

The `get_template_details` tool provides the context needed to enrich your vector index. You store the field definitions alongside the template text for better retrieval accuracy. This makes your index smarter. When the agent looks for a W-9 form, it retrieves both the template structure and the required field names in one go.

Setup guide

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

Index the output of `list_doc_templates` into your vector store. Once indexed, your LlamaIndex agent can perform semantic searches to find the most relevant template for any user request.

Call `list_recently_generated_docs` to get a list of your latest files. Adding these to your LlamaIndex knowledge base allows you to chat with your history and find specific document IDs instantly.

Yes, use `get_template_field_schema` to grab the data requirements for any template. LlamaIndex can store these schemas, helping the agent construct perfect payloads for the generation API.

You define the persistence layer in your LlamaIndex setup. By indexing the output of the Docdown MCP Server, you keep your document knowledge available across multiple sessions.

Data is retrieved via a single endpoint token that authenticates your requests to Docdown. Your document IDs and metadata are processed only within your local index, keeping your information isolated from other users.

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