How to Use the Dovetail MCP in LlamaIndex

Q: How do I index Dovetail research notes in LlamaIndex?

Initialize the BasicMCPClient to connect the MCP Server and load text from listnotes into your LlamaIndex vector index. This makes your Dovetail qualitative feedback fully searchable.

Q: Can I query Dovetail insights using LlamaIndex RAG?

Yes, your LlamaIndex query pipeline pulls live data using listinsights to ground its answers. This prevents your model from generating fake Dovetail feedback.

Q: Does this Dovetail MCP Server support asynchronous LlamaIndex runs?

Yes, you load the Dovetail tools using totoollistasync within your LlamaIndex agent. This keeps your search queries fast even when fetching large volumes of Dovetail notes.

Q: How do I limit which Dovetail projects LlamaIndex can read?

You pass specific project IDs to getprojectdetails to restrict your LlamaIndex vector indexer to active Dovetail studies. This avoids indexing irrelevant workspaces.

Index Dovetail research notes into LlamaIndex vector stores for grounded RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dovetail MCP to LlamaIndex

Create your Vinkius account to connect Dovetail 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 Dovetail with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Dovetail qualitative research into LlamaIndex

The `list_notes` tool feeds raw qualitative data from your Dovetail workspace directly into LlamaIndex's indexing pipeline. Your ingestion pipeline maps these notes into vector nodes. By grounding your LlamaIndex queries in real Dovetail user data, you eliminate model hallucinations. You get accurate search results every time.

Build RAG pipelines with the Dovetail MCP Server

The `list_insights` tool lets your LlamaIndex query engine pull live context directly from your Dovetail workspace using the MCP Server. Your model queries actual findings instead of guessing. This setup ensures your LlamaIndex synthesized answers match your actual Dovetail user research. You build a reliable knowledge base.

Ground LlamaIndex responses in Dovetail workspace feedback

The `create_insight` tool writes synthesized LlamaIndex research conclusions back to your Dovetail workspace after running a query. Your automated pipeline saves hours of manual entry. Your LlamaIndex agent verifies access using `list_workspace_members` before executing any write operations on Dovetail projects. This verification keeps your data secure.

Setup guide

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

Initialize the `BasicMCPClient` to connect the MCP Server and load text from `list_notes` into your LlamaIndex vector index. This makes your Dovetail qualitative feedback fully searchable.

Yes, your LlamaIndex query pipeline pulls live data using `list_insights` to ground its answers. This prevents your model from generating fake Dovetail feedback.

Yes, you load the Dovetail tools using `to_tool_list_async` within your LlamaIndex agent. This keeps your search queries fast even when fetching large volumes of Dovetail notes.

You pass specific project IDs to `get_project_details` to restrict your LlamaIndex vector indexer to active Dovetail studies. This avoids indexing irrelevant workspaces.

The MCP Server handles Dovetail workspace member details and research insights within a zero-trust, isolated sandbox environment during LlamaIndex runs. Vinkius manages authentication tokens securely, meaning your Dovetail team roster and user quotes are never exposed to public models.

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