Metrics

Model Context Protocol

MCP

In short

The Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude access external tools and data sources, such as a CRM, calendar or marketing data.

The Model Context Protocol (MCP) is an open standard introduced by Anthropic in 2024. It defines how AI assistants talk to external tools. Instead of copying data into a chat, the assistant fetches it directly through an MCP server.

How MCP works

  • An MCP server describes a set of tools with name, purpose and inputs.
  • An MCP client such as Claude connects to the server, usually via OAuth or an API key.
  • When you ask a question, the model decides which tools it needs, calls them and processes the results.

That way, an AI agent can, in a single conversation, fetch campaign data, compare two periods and write a report from it.

MCP in marketing

For marketing teams, MCP is interesting mainly because data sources can be combined: campaign performance, CRM, calendar, documents. LeadMetrics offers its own MCP server that lets Claude query projects, metrics and performance down to ad level, including leads, deals and ROAS. It doesn't expose personal lead data. More on the AI Marketing Copilot page.

Ready for better tracking?

Try LeadMetrics free for 10 days and see which campaigns actually drive revenue.
Start a 10 day trial

Frequently asked questions

An MCP server gives an AI assistant tools, such as "list projects" or "get performance". The assistant decides on its own when to call which tool and gets the results back as data.

Guides on this topic

Advertising8 min read

AI Marketing Team for Lead Generation: What Agents Can Take Over - and What Data They Need

What an AI marketing team of agents for research, ads, inbox and analysis can do, where humans need to stay in the loop and why, in lead generation, it optimizes for the wrong leads without CRM data.

Read guide
Metrics6 min read

Analyze Campaigns with Claude: Your Daily Report via the LeadMetrics MCP Server

How to connect Claude to LeadMetrics and get a campaign report every day: setup, prompt templates for top and bottom ads, week-over-week comparison and client updates.

Read guide
Advertising7 min read

Ad Naming Convention: How to Make Your Creatives Analyzable

With a fixed scheme for ad names, you see which hook, offer and format brings deals - in the dashboard, in UTMs and in AI analyses with Claude.

Read guide

Articles on this topic

Related terms

All terms

AI Agent

An AI agent is an AI system that completes a task on its own over several steps: it fetches data, uses tools and decides on the next step instead of just answering a single question.

KPI · Key Performance Indicator

A KPI (key performance indicator) is a measurable metric that shows whether you are reaching an important business or marketing goal.

Benchmark

A benchmark is a reference value you measure your own metrics against, such as industry averages, past periods or your own best-performing campaign.

Click-Through Rate

Click-through rate (CTR) is the percentage of people who see an ad and then click on it, calculated as clicks divided by impressions.

Conversion Rate

Conversion rate is the percentage of visitors or leads who complete a desired action, such as submitting a form or making a purchase.

Cost per Acquisition

Cost per acquisition (CPA) measures the average ad spend per conversion such as a purchase or closed deal: ad spend divided by the number of conversions.