Persuasion Taxonomy MCP logo

Persuasion Taxonomy MCP

Plans, reviews, and tests marketing copy using nine reader questions, 766 persuasion techniques, and A/B test calculations.

Install Persuasion Taxonomy MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "persuasion-taxonomy-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@coppica/persuasion-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 9 tools correctly ().

Overview

Persuasion Taxonomy MCP MCP server gives AI clients a structured framework for planning and reviewing marketing copy. It provides nine reader questions, a catalog of 766 persuasion techniques drawn from real advertising, copy diagnostics, and A/B test calculations through MCP tools. Use it when an agent needs to plan a landing page, diagnose weak conversion copy, compare headlines, or interpret experiment results. The hosted endpoint uses Streamable HTTP, and a local npm-based stdio mode is also available.

Use cases

  • Plan a landing page around reader questions
  • Diagnose why marketing copy is not converting
  • Compare headlines before an A/B test
  • Find less predictable persuasion techniques
  • Interpret A/B test results

Key features

  • Nine-question copy planning framework
  • Catalog of 766 persuasion techniques
  • Marketing copy diagnosis
  • Headline and claim checks
  • A/B test planning and result analysis
  • Hosted HTTP and local stdio access

Tools9

What Persuasion Taxonomy MCP lets your agent do. Expand a tool for its parameters.

Verified live~5.9k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

10/10 checks healthy over the last 45d

What it can do

From the 9 tools this server returned when we ran it; 9 declare their own safety hints.

Read-only tools · 9
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age12 days
Maintainers1

Observed 2026-10-17 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @coppica/persuasion-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads256Package downloads in the last 30 days.
Last commit7d agoMost recent push to the default branch.
MaintenanceActively maintainedStatus declared by the project or listing owner.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed9Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Persuasion Taxonomy MCP works

What Persuasion Taxonomy MCP MCP server does

Persuasion Taxonomy MCP MCP server helps an AI plan, inspect, and improve marketing copy. Its framework is based on nine questions readers may ask while evaluating an advertisement, page, email, or sales letter. The questions cover attention, audience fit, problem awareness, beliefs, trust, desired outcomes, objections, urgency, and confidence in the speaker.

The server also exposes a catalog of 766 persuasion techniques documented from real advertisements, sales letters, emails, and pages dating from the 1920s to the present. Technique entries include examples and information about situations where a technique can fail. Catalog data is available under CC BY 4.0, while the server code is MIT licensed.

How it works

The MCP server supplies catalog content, scoring logic, and calculations. It does not make AI calls itself. The connected model decides how to use the tools and produces the writing or analysis. Submitted copy, briefs, and test numbers are used for the request and then discarded; the hosted service records tool calls and ordinary short-term web request logs.

The main workflow tools are:

  • plan_marketing_copy structures a brief around the nine reader questions.
  • diagnose_marketing_copy identifies answered and skipped questions and flags writing that may sound machine-generated.
  • explain_why_not_converting works backward from a conversion problem to a likely unanswered question.
  • find_persuasion_techniques searches the technique catalog.
  • get_persuasion_technique returns a technique's details, examples, and possible failure modes.
  • check_headlines compares headlines and recommends two candidates to test.
  • check_marketing_claims reviews claims, promises, superlatives, and calls to action.
  • plan_ab_test estimates test requirements and defines a useful test frame.
  • read_ab_test_result interprets results and identifies cases where the result may be unreliable.

Setup and configuration

The hosted endpoint is https://taxonomy.coppica.com/mcp. Add it to an MCP client as a remote Streamable HTTP server; no API key or sign-in is required. Claude Code can register it with claude mcp add --transport http, while Cursor and VS Code can add the endpoint to their MCP configuration files.

For local execution, configure a client to run npx -y @coppica/persuasion-mcp. The repository also provides a Claude Code plugin that installs the server and a short usage skill. Four prompt resources are included: /roast, /brief, /why-not-converting, and /next-test. The nine-question framework is available as a readable resource.

Tools and capabilities

Persuasion Taxonomy MCP MCP server supports copy planning, copy diagnosis, conversion troubleshooting, technique discovery, claim review, headline comparison, and A/B test planning or analysis. It is suited to agents working on landing pages, advertisements, emails, sales letters, and related marketing copy.

The catalog is distributed as a snapshot in the repository. Developers can refresh it with npm run export-data, which requires read access to Coppica's database. The exported HTTP handler accepts a web-standard Request and returns a Response, allowing deployment in environments such as Next.js, Vercel, Cloudflare functions, or Node 18 and later.

Limitations and notes

The server does not generate or evaluate copy through its own language model. Output quality depends on the connected model's use of the tools. Hosted requests are not retained as submitted content, but tool-call and ordinary request logs are kept for a short period according to the service's privacy policy.

The technique catalog and server code have separate licenses: MIT applies to the code, and CC BY 4.0 applies to the catalog data. The local catalog is a snapshot unless it is refreshed from the source database.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Persuasion Taxonomy MCP

Persuasion Taxonomy MCP is an MCP server that connects AI clients to a catalog of 766 persuasion techniques and tools for planning, diagnosing, and testing marketing copy. It includes nine reader questions, headline and claim checks, conversion analysis, and A/B test calculations. It requires no API key and makes no AI calls.

Install it by adding the hosted Streamable HTTP endpoint, https://taxonomy.coppica.com/mcp, to an MCP client, or run `npx -y @coppica/persuasion-mcp` for local stdio access. No API key or sign-in is required.

Yes, Persuasion Taxonomy MCP works with Cursor through its MCP configuration. Add a server named `persuasion-taxonomy` with the hosted URL `https://taxonomy.coppica.com/mcp` in `.cursor/mcp.json`.

It can analyze landing pages, advertisements, emails, sales letters, headlines, claims, and calls to action. Its tools can diagnose skipped reader questions, explain possible conversion problems, and compare headline options.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPersuasion Taxonomy MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/persuasion-taxonomy-mcp?style=directory)](https://allmcps.com/mcp/persuasion-taxonomy-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/persuasion-taxonomy-mcp"><img src="https://allmcps.com/api/badge/persuasion-taxonomy-mcp?style=directory" alt="Persuasion Taxonomy MCP on AllMCPs" /></a>