La Growth Machine — B2B Outreach & Pipeline Analytics

La Growth Machine — B2B Outreach & Pipeline Analytics

Analyze LinkedIn & email outreach campaigns, track pipeline performance, and review lead conversations for RevOps, Sales Managers, and SDR teams.

Category
Visit Server

README

/*

  • Copyright 2026 La Growth Machine
  • Licensed under the Apache License, Version 2.0 (the "License");
  • you may not use this file except in compliance with the License. */

La Growth Machine — B2B Outreach & Pipeline Analytics

Analyze LinkedIn & email outreach campaigns, track pipeline performance, and review lead conversations — for RevOps, Sales Managers, and SDR teams.


La Growth Machine connects your AI assistant to your outbound revenue stack — giving RevOps engineers, Sales Managers, and SDR teams instant access to campaign performance, lead engagement data, and message sequences across LinkedIn and email. Stop switching between dashboards to answer "what's working?". Ask your AI instead.


Compatibility

This MCP server works with any MCP-compatible AI client:

  • Claude Desktop (Anthropic)
  • Claude Code (CLI & IDE extensions)
  • Cursor, Windsurf, and other MCP-enabled editors
  • Any client that supports the Model Context Protocol

Why connect La Growth Machine to your AI?

Your outreach data is only useful if you can act on it. With this extension, your AI becomes your outbound analyst — surfacing what's working, what's stalling, and where to focus next.

Built for:

  • RevOps & GTM Engineers who orchestrate the revenue stack and need fast, flexible access to campaign performance
  • Sales Managers & Team Leads who need visibility on team activity and pipeline contribution without digging through dashboards
  • Sales Reps managing live conversations and follow-ups across channels

What you can do

Analyze campaign performance Compare reply rates, acceptance rates, and conversion metrics across campaigns — and get a diagnosis, not just a table.

Audit your message sequences Pull the full message flow for any campaign. Identify weak touchpoints or flag messages that may be dragging down your reply rate.

Explore leads and audiences Browse leads by audience, filter by status, or deep-dive into a specific lead's profile: company, role, email, LinkedIn URL.

Read full conversation threads Get the complete message history for any lead across all channels (email + LinkedIn) — with context, not just raw logs.

Track engagement activity View all actions taken on a lead: connection requests sent, messages delivered, replies received, follow-ups triggered.

Build audiences from a LinkedIn URL Drop in a LinkedIn search, Sales Navigator search, or LinkedIn post URL — your AI creates the audience and triggers the lead import in one shot.

Personalize AI-generated outreach Save tone and style preferences per La Growth Machine identity, so your AI generates on-brand messages that match your voice.


Go deeper with LGM Skills

The MCP gives your AI access to your data. LGM Skills give it the expertise to act on it.

Skills are specialized AI instructions that work hand-in-hand with this MCP — the MCP surfaces your campaign data, the skill knows how to analyze it and turn it into actionable recommendations.

Available now

Campaign Analyzer Pulls your campaign stats and sequences via the MCP, then runs a structured analysis to identify what's hurting your reply rate — weak subject lines, poor sequencing, missing follow-ups — and gives you prioritized recommendations to fix it.

"Analyze my 'VP Sales Q2' campaign and tell me what to improve."

Coming soon

  • Segmentation Advisor — Audit your audience targeting and flag ICP mismatches before they hurt performance
  • Copywriting Coach — Review your message sequences against outreach best practices and rewrite underperforming steps

All LGM Skills are available at: https://github.com/laGrowthMachine/gtm-system


Usage Examples

Diagnose a campaign that's underperforming

You: "My 'VP Sales Q2' campaign has a low reply rate. Show me the message sequence and stats."

AI: Fetches campaign KPIs (acceptance rate, reply rate, conversion) and the full message sequence. Identifies which steps have drop-offs and flags messages that may be too generic or too long.

Want deeper recommendations? Install the Campaign Analyzer skill to get structured, actionable improvements — not just data.


Get a full picture of a lead before calling them

You: "Show me everything about John Smith at Acme Corp — conversation history, activity log, and their LinkedIn profile."

AI: Pulls the full engagement timeline: messages sent and received, connection status, reply content — giving you a complete pre-call brief in seconds.


Weekly team pipeline review

You: "List all running campaigns, their reply rates, and flag anything below 10% acceptance."

AI: Generates a structured overview of active campaigns with key metrics, highlights underperformers, and surfaces which campaigns need attention.

Want to fix the underperformers? Install the Campaign Analyzer skill for ICP and copy recommendations.


Build an audience straight from a Sales Nav URL

You: "Create a new audience called 'DACH VPs of Sales' from this Sales Nav search — use my main LinkedIn identity. Here's the URL: https://www.linkedin.com/sales/search/people?..."

AI: Calls list_identities to resolve your main identity, then create_audience_from_linkedin_url to kick off the import. The import runs asynchronously — list your audiences and check progress with get_audience.


Audit your outreach sequence before launch

You: "Show me the message flow for my 'DACH Enterprise' campaign — I want to check the timing and content before it goes live."

AI: Displays the full sequence with message content, channel (email vs LinkedIn), and step order — ready for a final review.

Not sure if the copy is strong enough? The Copywriting Coach skill (coming soon) will review each message against outreach best practices and suggest rewrites.


Available Tools

Tool Description
list_campaigns List and filter campaigns by status, name, or date
get_campaign_stats Acceptance rate, reply rate, conversions, and more
get_campaign_messages Full message sequence with content and channel order
get_audience Audience name, size, type, and import status
get_audience_leads Leads list with name, company, role, email, LinkedIn
get_lead_logs Full activity history for a lead across all channels
get_lead_conversations All conversation threads with a lead
get_conversation_messages Complete message thread in a conversation
save_identity_preference Save tone/language/style for AI-generated content
create_audience_from_linkedin_url Create or populate an audience from a LinkedIn / Sales Nav search or post URL
list_identities List your connected LinkedIn / email identities — needed to pick an identityId
get_conversations_to_reply Inbox conversations waiting for your reply (lead spoke last, thread open)
get_unread_conversations Unread inbox conversations, newest first
get_favourite_conversations Favourited / starred conversations, optionally only those that replied
search_conversations Full-power inbox search — filter by text, identity, campaign, audience, channel, status, dates, flags
snooze_conversation Snooze a conversation until later (hide from the active inbox)
unsnooze_conversation Un-snooze a conversation back into the active inbox
archive_conversation Archive a conversation (remove from the active inbox)
unarchive_conversation Restore an archived conversation to the active inbox
list_members List account members — needed to pick a memberId for sending LinkedIn messages
send_linkedin_message Send a LinkedIn text or voice message to a lead from a connected identity
send_email_message Send an email to a lead from a connected email identity (new thread or reply)

Setup

Claude Desktop

  1. Download lgm-mcp.mcpb
  2. Double-click to open with Claude Desktop
  3. Click Install
  4. Enter your LGM API key — find it in Settings > API
  5. Start chatting with your campaigns

Claude.ai (web connector)

  1. Go to claude.aiSettingsConnectorsAdd custom connector

  2. Enter the following URL:

    https://mcpapp.lagrowthmachine.com/mcp
    
  3. Open Advanced parameters and fill in the OAuth credentials:

    Field Value
    OAuth Client ID Your LGM account email
    OAuth Client Secret Your LGM API key — find it in Settings > API
  4. Click Save.

  5. Back on the Connectors list, click Connect on the La Growth Machine line — Claude.ai will go through the authentication flow and the connector will be active.

Other MCP clients (Claude Code, Cursor, etc.)

claude mcp add --transport http --scope user LaGrowthMachine \
  https://mcpapp.lagrowthmachine.com/mcp \
  --header "X-LGM-API-KEY: <your-api-key>"

Replace claude mcp add with your client's equivalent MCP configuration command.

Your API key is stored securely in the OS keychain (macOS Keychain / Windows Credential Manager). No La Growth Machine data is stored locally or shared with third parties.


Privacy

This extension connects to the La Growth Machine API using your API key. Data is fetched on-demand and used only within your AI conversation. Nothing is stored beyond your API key (in the OS keychain). Your data is not shared with any third party.

Full policy: lagrowthmachine.com/privacy-policy

Usage analytics & opt-out

To understand which tools are used, the server sends a single first-party analytics event on each tool call:

  • What is sent: the event name (mcp_tool_called, or mcp_preference_saved for save_identity_preference) and the tool name only. No conversation content, lead data, message bodies, or arguments are ever included.
  • Where it goes: La Growth Machine's own API at https://apiv2.lagrowthmachine.com/flow/tracking/mcp — the same first-party service you authenticate against with your API key. Nothing is sent to any third party.
  • Failure handling: the request is fire-and-forget; if it fails it is silently ignored and never blocks a tool result.

Opt-out: analytics is fully optional.

  • Claude Desktop: enable the "Disable usage analytics" toggle in the extension settings.
  • Self-hosted / other clients: set the environment variable LGM_DISABLE_TELEMETRY=true. When set, the server sends no analytics requests at all.

Support

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured