How to Use the Reply.io MCP in LlamaIndex

Q: How do I index Reply.io campaign data into LlamaIndex using the MCP Server?

Use listcampaigns to fetch your outreach campaigns, then wrap the JSON output in LlamaIndex Document objects. You can then ingest them into your vector store for semantic querying.

Q: Can a LlamaIndex agent decide to pause a Reply.io prospect?

Yes, by using pauseperson within a FunctionAgent. The agent evaluates index query results and calls the tool if it detects a conflict.

Q: How do I avoid duplicate prospects when using LlamaIndex with Reply.io?

Your agent can check existing entries using listpeople before calling addperson. Indexing the results first allows for fast, local deduplication checks.

Q: Does this MCP Server support checking email sender configurations?

Yes, the listemailaccounts tool retrieves your connected sending profiles. You can index this data to let your agent verify which domains are active.

Q: What happens to my sender email account details during indexing?

Your email account configurations fetched via listemailaccounts are passed directly to your local LlamaIndex instance. Vinkius processes these credentials in ephemeral, isolated runtimes that delete all session data immediately after execution.

Index Reply.io campaign metrics and prospect histories into LlamaIndex to ground your agent in real outreach data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Reply.io MCP to LlamaIndex

Create your Vinkius account to connect Reply.io to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Reply.io with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index live outreach data for RAG

This MCP Server provides `list_people` to pull your entire prospect directory into LlamaIndex document objects. Once indexed, your agent can perform semantic searches to find which prospects match specific historical profiles before launching new campaigns. Instead of querying raw databases, you build a searchable knowledge base of your sales pipeline. This ensures your RAG applications use actual prospect context instead of guessing.

Ground LlamaIndex agent responses in actual stats

Stop guessing which campaign works. The `get_campaign_stats` tool feeds live performance data directly into your LlamaIndex query engines. By linking `list_campaigns` with vector indexes, the agent compares current run rates against historical benchmarks. By connecting this MCP Server, you can query actual performance.

Manage prospect states via index lookups

Look, double-emailing a hot lead is embarrassing. The `pause_person` tool allows your LlamaIndex agent to suspend sequences for contacts identified during semantic search queries. You can quickly reactivate them using `resume_person` once the database index updates. This prevents embarrassing double-outreach situations by keeping your indexing pipeline in lockstep with Reply.io.

Setup guide

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

Use `list_campaigns` to fetch your outreach campaigns, then wrap the JSON output in LlamaIndex Document objects. You can then ingest them into your vector store for semantic querying.

Yes, by using `pause_person` within a FunctionAgent. The agent evaluates index query results and calls the tool if it detects a conflict.

Your agent can check existing entries using `list_people` before calling `add_person`. Indexing the results first allows for fast, local deduplication checks.

Yes, the `list_email_accounts` tool retrieves your connected sending profiles. You can index this data to let your agent verify which domains are active.

Your email account configurations fetched via `list_email_accounts` are passed directly to your local LlamaIndex instance. Vinkius processes these credentials in ephemeral, isolated runtimes that delete all session data immediately after execution.

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