How to Use the Gmelius MCP in LlamaIndex

Q: Can I query my Gmelius boards using semantic search?

Yes, you can. By indexing the output of listgmeliusboardcards and getgmeliusboard, your LlamaIndex agent can search across your project boards to find relevant tasks.

Q: Does this Gmelius and LlamaIndex setup support live updates via MCP?

You can set up a recurring task to call listgmeliusconversations and upsert the new threads into your vector index, keeping your knowledge base fresh.

Q: Can the agent check if the Gmelius API is online?

The agent can execute checkgmeliusstatus as part of its initialization step to ensure the connection is live before attempting to pull and index data.

Index your Gmelius shared inbox conversations and board cards directly into your LlamaIndex knowledge base using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gmelius MCP to LlamaIndex

Create your Vinkius account to connect Gmelius 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 Gmelius with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index shared inbox conversations for RAG

Turn your email archives into an active knowledge base. Your LlamaIndex agent can run `list_gmelius_conversations` to fetch recent threads and `get_gmelius_conversation` to extract the full message history. This text is then indexed directly into your vector store. Instead of guessing what a customer was told last week, your agent queries the vector index. You get answers grounded in real, historical email exchanges, cutting down on duplicate replies and inconsistent support.

Query your Kanban boards semantically

Stop hunting through endless lists of tasks. This MCP Server lets your LlamaIndex pipelines pull board data using `list_gmelius_boards` and `list_gmelius_board_cards` to index your team's project pipeline. Once indexed, you can ask your agent plain-English questions like what your team is currently working on. The agent searches the vector store and matches the query against live card details.

Access Gmelius templates with LlamaIndex

Give your agents access to your team's approved email templates. By calling `list_gmelius_templates`, your RAG pipeline can retrieve the correct pre-written responses and match them to incoming user queries. This ensures your agent's answers match your brand's voice. It retrieves the template, fills in the specific details using retrieved context, and prepares a draft without hallucinating the core message.

Setup guide

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

Use the LlamaIndex MCP tool spec to connect to your Vinkius endpoint. From there, you can load tool outputs like `list_gmelius_conversations` directly into your document ingestion pipeline.

Yes, you can. By indexing the output of `list_gmelius_board_cards` and `get_gmelius_board`, your LlamaIndex agent can search across your project boards to find relevant tasks.

You can set up a recurring task to call `list_gmelius_conversations` and upsert the new threads into your vector index, keeping your knowledge base fresh.

The agent can execute `check_gmelius_status` as part of its initialization step to ensure the connection is live before attempting to pull and index data.

Your email threads and board data are pulled directly from the Gmelius API and sent straight to your vector store. Vinkius handles the connection token securely in an ephemeral sandbox, so your raw communication data is never cached on our servers.

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