How to Use the Mailshake MCP in LlamaIndex

Q: How do I configure LlamaIndex to use the Mailshake MCP Server?

Install llama-index-tools-mcp and set up a BasicMCPClient. Wrap it in McpToolSpec and call totoollistasync() to make the tools available to your FunctionAgent.

Q: Can LlamaIndex search through my Mailshake campaign recipients?

Yes. You use listcampaignrecipients to pull the contact lists. LlamaIndex embeds those records, allowing you to run natural language queries to find specific targets across all active sequences.

Q: Does LlamaIndex automatically pause Mailshake campaigns?

Only if you give the agent permission to execute the pauseoutreachcampaign tool. By default, you can restrict the allowed tools to read-only operations like listcampaignleads during setup.

Q: How do I filter which Mailshake tools LlamaIndex can access?

Use the allowedtools parameter when initializing your agent. This prevents the system from accidentally calling state-changing endpoints while building your semantic index.

Index your Mailshake outreach data directly into LlamaIndex via this MCP Server to build queryable 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 Mailshake MCP to LlamaIndex

Create your Vinkius account to connect Mailshake 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 Mailshake with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Campaign Lead History

The `get_lead_history` tool pulls raw engagement logs so LlamaIndex can embed them into your vector store. Your RAG setup ingests every open, click, and reply, turning scattered API data into a unified, searchable index. You query the index to find out why deals stalled. Instead of guessing, your agent retrieves the actual touchpoints and grounds its answers in real historical data.

Query Mailshake MCP Server Data

The `list_outreach_messages` tool feeds your knowledge base with the exact text sent to prospects. When a user asks what pitch worked best last quarter, LlamaIndex runs a semantic search over the ingested message data. It combines this with `get_message_content` to pull the full email bodies. You get answers based on the actual words your sales team wrote, completely eliminating AI hallucinations.

Combine Live Stats with Documents

The `list_outreach_campaigns` and `get_campaign_details` tools fetch live performance metrics. You configure your FunctionAgent to pull these stats and compare them against your internal sales playbooks. You set up the `McpToolSpec` to give the agent access to both the live Mailshake API and your local PDFs. The agent reads the current reply rate and cross-references it with your documented best practices to suggest improvements.

Setup guide

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

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Wrap it in `McpToolSpec` and call `to_tool_list_async()` to make the tools available to your FunctionAgent.

Yes. You use `list_campaign_recipients` to pull the contact lists. LlamaIndex embeds those records, allowing you to run natural language queries to find specific targets across all active sequences.

Only if you give the agent permission to execute the `pause_outreach_campaign` tool. By default, you can restrict the allowed tools to read-only operations like `list_campaign_leads` during setup.

Use the `allowed_tools` parameter when initializing your agent. This prevents the system from accidentally calling state-changing endpoints while building your semantic index.

Vinkius operates a zero-trust V8 Isolate Sandbox for the connection. Your raw email bodies and prospect replies are fetched securely and embedded locally in your own vector database. The MCP server is ephemeral and retains zero state after the request completes.

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