GuidesLinkedIn Ads MCP

LinkedIn Ads MCP Server

Connect Claude, ChatGPT, or any AI tool to your LinkedIn Ads account. Manage campaigns, build creatives, qualify lead-gen responses, and analyze B2B performance with natural language.

What is the LinkedIn Ads MCP?

The Pipeboard LinkedIn Ads MCP (Model Context Protocol) Server connects AI assistants like Claude, ChatGPT, and custom agents to the LinkedIn Marketing API. Manage sponsored campaigns, build creatives, qualify lead-gen responses, and analyze B2B performance through natural language.

Instead of wiring up the LinkedIn Marketing API yourself, you get instant access to campaign management, demographic analytics, audience targeting, lead-gen forms, and conversion tracking.

Key features:

50+ pre-built tools covering campaigns, creatives, audiences, lead-gen, and conversions
Works with Claude Desktop, ChatGPT, Python, n8n, and any MCP client
B2B demographic analytics — break down performance by company, industry, seniority, and job function
Lead-gen forms: list forms, pull responses, and inspect individual lead details
Creative builders for single-image, carousel, dynamic, and inline dark-post ads
Safety-first: creatives are created in DRAFT and write tools support dry-run previews

What you can do

The real tools the LinkedIn Ads MCP exposes

Accounts & campaigns

  • List ad accounts and account details
  • List & filter campaigns and campaign groups
  • Create campaigns and campaign groups
  • Pause, resume, and archive campaigns
  • Update budget, bid, schedule, and campaign name

Creatives

  • List and fetch creatives
  • Upload images and videos
  • Build single-image, carousel, and dynamic creatives
  • Create inline dark-post (sponsored) creatives
  • Change creative status (pause / resume / draft)

Analytics & reporting

  • Campaign, account, and creative analytics over any date range
  • Campaign-group analytics and campaign statistics
  • Demographic breakdowns (company, industry, seniority, function)
  • Attributed revenue reporting

Audiences & targeting

  • Search targeting entities and estimate audience size
  • Create, list, get, and attach matched audiences
  • Build website-retargeting audiences
  • Resolve demographic URNs to readable names

Lead generation

  • List lead-gen forms and inspect a single form
  • Pull lead-form responses
  • Drill into individual lead response details

Conversions & tracking

  • List, create, and update conversions
  • Associate conversions with campaigns
  • Read the Insight Tag and tracking parameters
  • Get budget & pricing forecasts before launch

Getting Started

Set up in under 2 minutes

1. Sign up for a Pipeboard account:

pipeboard.co/auth/signup →

2. Connect your LinkedIn Ads account:

pipeboard.co/connections →

3. Add the MCP server to Claude (or another MCP client):

https://linkedin-ads.mcp.pipeboard.co/

Use this URL as a Streamable HTTP MCP server in your client. Authentication is handled automatically through your Pipeboard session.

Connect to Your AI Tool

The LinkedIn Ads MCP works with any MCP-compatible client. Just add the server URL and start managing your campaigns with natural language.

Claude Pro / Max

Recommended
  1. 1.Open claude.ai/customize/connectors
  2. 2.Click "Add custom connector"
  3. 3.URL: https://linkedin-ads.mcp.pipeboard.co/

ChatGPT

Developer mode
  1. 1.Enable Developer mode in ChatGPT Settings
  2. 2.Settings → Apps → Advanced → Developer mode
  3. 3.Create app with MCP URL

Claude Code

CLI / VS Code

Run this command in your terminal:

claude mcp add --transport http pipeboard-linkedin-ads https://linkedin-ads.mcp.pipeboard.co/

Then type /mcp in Claude Code to authenticate with Pipeboard.

Alternative: use an API token for instant setup (no browser auth needed):

claude mcp add --transport http pipeboard-linkedin-ads https://linkedin-ads.mcp.pipeboard.co/?token=pk_...

Get your token at pipeboard.co/api-tokens

Claude Desktop JSON configuration:

Add this to your Claude Desktop MCP settings (Settings → MCP Servers → Add):

claude_desktop_config.json
{
  "mcpServers": {
    "linkedin-ads": {
      "url": "https://linkedin-ads.mcp.pipeboard.co/"
    }
  }
}

Try these prompts

Campaign Overview

"List my LinkedIn ad accounts and show campaign performance for the last 30 days"

B2B Demographics

"Break down my top campaign by industry, seniority, and job function — which segments convert best?"

Lead-Gen Review

"Pull the latest responses from my LinkedIn lead-gen forms and summarize the new leads"

Budget Optimization

"Compare cost-per-lead across campaigns. Where should I shift budget to lower CPL?"

Best Practices

  • Create creatives in DRAFT, then review before activating them
  • Use dry-run on create/update tools to preview the LinkedIn call before applying it
  • Estimate audience size with targeting search before launching a campaign
  • Lean on demographic breakdowns (industry, seniority, function) to find your best B2B segments
  • Get a budget & pricing forecast before committing spend
  • Pass dates as ISO YYYY-MM-DD strings and pass numeric account IDs without the urn prefix

Frequently Asked Questions

Which LinkedIn Ads features does the MCP support?

Campaigns and campaign groups, creatives (single-image, carousel, dynamic, and inline dark posts), image and video uploads, demographic analytics, audience targeting and retargeting, lead-gen forms and responses, and conversion tracking with the Insight Tag.

Do I need a LinkedIn developer app or API key?

No. You connect your LinkedIn Ads account once at pipeboard.co/connections via OAuth, and Pipeboard handles the LinkedIn Marketing API access for you. The MCP authenticates through your Pipeboard session or an API token.

Can I read lead-gen form responses?

Yes. The MCP can list your lead-gen forms, pull form responses, and drill into the details of an individual lead so an assistant can summarize and qualify new leads for you.

Will it create or change live campaigns without my approval?

Creatives are created in DRAFT by default, and write tools support a dry-run preview that returns the exact LinkedIn call without applying it — so you can review changes before they go live.

Does it work with ChatGPT and other MCP clients?

Yes. The server speaks Streamable HTTP MCP, so it works with Claude (Desktop, Code, Pro/Max), ChatGPT developer mode, Python, n8n, and any MCP-compatible client.

Ready to connect your AI tools to LinkedIn Ads?

Get started with the LinkedIn Ads MCP in under 2 minutes.