How to Use the DocBreach MCP in LlamaIndex

Q: How does DocBreach improve retrieval accuracy in LlamaIndex RAG pipelines?

The server uses docs.read to strip out headers, footers, and scripts, leaving only pure Markdown. This clean input means your LlamaIndex embeddings represent actual technical content, which directly improves retrieval accuracy.

Q: Can I use DocBreach to update a LlamaIndex vector index dynamically?

Yes, your agent can call docs.map to check for new documentation pages on a target domain. If it finds new paths, it reads them with docs.read and inserts the new nodes directly into your existing index.

Q: Does this tool require an external search engine API key to find documentation?

No, docs.discover finds documentation portals using built-in discovery logic without requiring any external search API subscriptions. The entire lookup runs through the secure Vinkius infrastructure.

Feed clean, parsed documentation directly into your LlamaIndex vector stores without managing fragile scrapers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocBreach MCP to LlamaIndex

Create your Vinkius account to connect DocBreach 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 DocBreach with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build clean documentation indexes for LlamaIndex RAG

`docs.read` converts raw documentation pages, OpenAPI specs, and PDFs into clean, structured Markdown. Your LlamaIndex ingestion pipeline takes this output and splits it into nodes without choking on HTML boilerplate or navigation links. This clean formatting means your vector embeddings capture actual technical details instead of website menus. Your agent queries the resulting index to retrieve precise API usage instructions without hallucinating parameters.

Map API structures before running document ingestion

`docs.map` retrieves the entire table of contents for a developer portal in a single call. This DocBreach MCP Server tool lets your indexing pipeline inspect the structure and select exactly which sections to ingest into your vector database. Instead of running recursive web crawlers that waste API credits, your LlamaIndex agent targets only the relevant sub-pages. This structured approach ensures your index stays updated with the latest endpoints without bloating your storage.

Search developer portals directly inside the tool loop

`docs.search` queries specific documentation domains for targeted keywords like authentication or rate limits. When your LlamaIndex agent needs immediate context to resolve a query, this MCP tool retrieves precise content blocks. The tool restricts its search to the target site parameter to prevent external noise. Your agent immediately indexes the returned context, making it instantly queryable for subsequent multi-step operations.

Setup guide

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

The server uses `docs.read` to strip out headers, footers, and scripts, leaving only pure Markdown. This clean input means your LlamaIndex embeddings represent actual technical content, which directly improves retrieval accuracy.

Yes, your agent can call `docs.map` to check for new documentation pages on a target domain. If it finds new paths, it reads them with `docs.read` and inserts the new nodes directly into your existing index.

Install the MCP tool spec for LlamaIndex and initialize the basic client pointing to your Vinkius HTTP endpoint. Convert the client tools using the tool spec adapter and pass them to your LlamaIndex FunctionAgent.

No, `docs.discover` finds documentation portals using built-in discovery logic without requiring any external search API subscriptions. The entire lookup runs through the secure Vinkius infrastructure.

No, all target URLs and parsed documentation content remain strictly inside your ephemeral Vinkius sandbox. No external logging or caching of your queried API specs occurs, ensuring your document lookup history is never exposed.

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