How to Use the DocsBot MCP in LlamaIndex

Q: How does LlamaIndex ingest DocsBot knowledge sources?

LlamaIndex uses listbotknowledgesources to retrieve metadata for all training documents. The framework converts these paths into document nodes, letting you build a local semantic index of your bot's training data.

Q: Can I filter which DocsBot bots LlamaIndex can access?

Yes, you pass a list of allowed tools to McpToolSpec to restrict MCP tool access. This prevents LlamaIndex from querying sensitive endpoints like getdocsbotaccountmetadata while keeping public search tools active.

Q: How does LlamaIndex keep DocsBot index data fresh?

Your pipeline runs listrecentlyindexedbots to check for recent knowledge base updates. When a change is detected, LlamaIndex triggers a re-indexing job to update your local vector embeddings.

Q: Can LlamaIndex query DocsBot interaction logs?

Yes, LlamaIndex retrieves past Q&A pairs using listbotinteractionlogs. You index these logs into a specialized vector store to help your agent learn from previous customer support interactions.

Index live DocsBot knowledge bases into LlamaIndex vector stores to ground your RAG applications in real-time data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocsBot MCP to LlamaIndex

Create your Vinkius account to connect DocsBot 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 DocsBot with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index DocsBot sources into LlamaIndex vector stores

The `list_bot_knowledge_sources` tool pulls raw data source lists from your DocsBot instances directly into LlamaIndex document objects. Your pipeline processes these sources, converting URLs and PDFs into searchable vector embeddings. This setup eliminates manual sync steps. Your RAG pipeline queries live source data, ensuring your local vector store matches the exact training state of your production bots.

Ground LlamaIndex queries using this MCP Server

This MCP Server provides `ask_bot_question` to let LlamaIndex query your existing bot instances during query routing. The engine compares local vector search results with live bot answers to verify factual consistency. By routing queries through this server, you prevent hallucinations in customer-facing tools. Your system compares the live bot output against cached knowledge summaries to ensure absolute accuracy.

Track indexing status within LlamaIndex workflows

The `get_bot_knowledge_summary` tool retrieves the exact size and source count of your knowledge base for LlamaIndex index validation. Your index pipeline checks these metrics before executing a query to ensure the vector store is fully updated. If the source count drops or mismatches, your pipeline halts the query. This programmatic check prevents your agent from serving answers based on stale or deleted source documentation.

Setup guide

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

LlamaIndex uses `list_bot_knowledge_sources` to retrieve metadata for all training documents. The framework converts these paths into document nodes, letting you build a local semantic index of your bot's training data.

Yes, you pass a list of allowed tools to `McpToolSpec` to restrict MCP tool access. This prevents LlamaIndex from querying sensitive endpoints like `get_docsbot_account_metadata` while keeping public search tools active.

Your pipeline runs `list_recently_indexed_bots` to check for recent knowledge base updates. When a change is detected, LlamaIndex triggers a re-indexing job to update your local vector embeddings.

Yes, LlamaIndex retrieves past Q&A pairs using `list_bot_interaction_logs`. You index these logs into a specialized vector store to help your agent learn from previous customer support interactions.

Your support logs and bot credentials stay within your local host. The MCP Server handles all communication with DocsBot over an encrypted connection, preventing unauthorized access to your team's internal documentation.

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