How to Use the AgentMail MCP in LlamaIndex

Q: How do I load AgentMail MCP tools into LlamaIndex?

You install llama-index-tools-mcp via pip. Initialize a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call totoollistasync() to get the functions.

Q: Can LlamaIndex search across multiple AgentMail inboxes?

Your agent must first run listinboxes to get the target IDs. It can then iterate through them, pulling threads from each address to populate your vector store.

Q: How do I restrict which AgentMail MCP Server tools my LlamaIndex agent can use?

Pass an allowedtools filter when configuring the spec. You might want an agent to run getinbox and getthread for indexing, but block sendmessage to prevent accidental outbound emails.

Q: Will AgentMail work with LlamaIndex FunctionAgent?

Yes, you pass the generated tool list directly into the FunctionAgent constructor. The agent decides when to query the index and when to fire an email tool.

Turn your LlamaIndex RAG pipelines into active email participants that query, index, and reply to threads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentMail MCP to LlamaIndex

Create your Vinkius account to connect AgentMail 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 AgentMail with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live threads via the AgentMail MCP Server

RAG applications usually rely on static documents. By attaching the `agentmail-mcp` tools, your pipeline pulls live conversations straight from the inbox. The agent runs `get_thread` to grab an entire customer support exchange. You feed that raw thread data directly into your vector store. When a user asks about a specific client issue, the engine searches the indexed emails instead of hallucinating an answer. It grounds every response in actual communication records.

Build searchable attachment databases

Files trapped in an inbox are useless to a standard query engine. By connecting this MCP server, your LlamaIndex application uses `list_threads` to find messages with files, then calls `get_attachment` to download the base64 payloads. You decode those files and parse them using LlamaParse before chunking them into your index. Now your users can ask questions about a PDF contract that arrived via email five minutes ago.

Act on retrieved knowledge immediately

Finding the right information is only half the job. Once your engine retrieves the correct answer from the vector store, it can draft a response and trigger `reply_to_message` to send it back to the original sender. You keep the entire loop inside one application. The system marks the conversation as handled by firing `update_message` to change the read status. You build a fully autonomous support desk that learns from its own outbox.

Setup guide

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

You install `llama-index-tools-mcp` via pip. Initialize a `BasicMCPClient` with your Vinkius URL, wrap it in an `McpToolSpec`, and call `to_tool_list_async()` to get the functions.

Your agent must first run `list_inboxes` to get the target IDs. It can then iterate through them, pulling threads from each address to populate your vector store.

Pass an `allowed_tools` filter when configuring the spec. You might want an agent to run `get_inbox` and `get_thread` for indexing, but block `send_message` to prevent accidental outbound emails.

Yes, you pass the generated tool list directly into the `FunctionAgent` constructor. The agent decides when to query the index and when to fire an email tool.

Your raw message bodies and attachment payloads pass through a strict V8 Isolate Sandbox on Vinkius. The connection requires a single endpoint token, ensuring your proprietary inbox contents never leak to unauthorized clients during the indexing phase.

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