Persuasion Taxonomy MCP
A free, no-API-key MCP server that gives your AI a model of the reader's nine questions, so it can plan, critique, and improve marketing copy, and do the math behind A/B tests.
Plan copy before drafting (ad, landing page, sales letter, email, subject line, social post, headline, video script): which questions the piece must answer, which deserve the most words, and a few ways to answer each, from the established move to less expected ones, tuned by category, awareness level, and persuasion mode.
Diagnose or roast a draft: which reader questions it answers, weakly answers, or skips; the biggest gap and what readers do; whether the answers agree and run in a workable order; craft tells like em dashes and "it's not X, it's Y" lines; an opening-line swap test; and techniques to fill the gap.
Explain why marketing isn't converting from a symptom (low CTR, high bounce, reads but no action, abandonment, leads that don't buy, churn, low opens), pointing to the unanswered questions, what to check first, and the test that would confirm it.
Find persuasion techniques among 766+ documented ones by plain-language goal, reader question, format, or category, and look up any technique for its definition, why it works, when it backfires, real examples, related and opposite entries, and a citable link.
Check and compare headlines, hooks, and subject lines: what each line bets on, what fails outright, what a reader sees before the cutoff, evidence from real headline tests, and which two to test against each other (no scores out of ten).
Check claims and CTAs for vague superlatives, promises with no proof, results with no mechanism, and generic buttons, with a fix for each.
Plan an A/B test (visitors per version, days to run, framed as two answers to one reader question) and read a test result (lift, significance, confidence interval, plus warnings about small samples, sample ratio mismatch, peeking, and too many versions).
Extras: four ready-made prompts (
/roast,/brief,/why-not-converting,/next-test) and the nine questions as a readable resource. Nothing you send is stored, and the server makes no AI calls of its own.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Persuasion Taxonomy MCP roast this landing page draft — which of the nine questions does it skip?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Persuasion Taxonomy MCP
Most AI-written marketing copy fails for the same reason. The model answers every question the reader has with the most expected move, and the most expected move is exactly what readers have learned to skim past.
This server gives your AI a better model of the reader. Everyone who reads an ad, a page or an email is silently asking nine questions:
Why am I even reading this?
Is this written for me?
How bad is my problem, really?
Am I thinking about this correctly?
Can I trust the claim?
What does my life look like after?
What's stopping me from saying yes?
Why should I act right now?
Do I like and trust who's speaking?
Copy persuades when it answers the questions its goal needs, answers them truthfully, and the answers fit together. The server helps your AI plan copy around those questions, check a draft against them before anyone sees it, and reach past the obvious move for one of 767 persuasion techniques documented from real advertising. It also does the math behind A/B tests.
It's free and needs no API key. It makes no AI calls of its own, either: your model does the thinking, and the server only serves the catalog and runs plain code.
Connect it
The hosted server lives at https://taxonomy.coppica.com/mcp. Any client that accepts a remote MCP server (Streamable HTTP) can use that URL as it is.
Claude Code
claude mcp add --transport http persuasion-taxonomy https://taxonomy.coppica.com/mcpClaude Code plugin. This adds the server along with a short skill that tells Claude when to reach for it.
/plugin marketplace add Otha-Labs/persuasion-mcp
/plugin install persuasion-taxonomy@persuasion-taxonomyClaude, ChatGPT and other apps with custom connectors. Add a custom connector and paste in the URL above. There's nothing to sign in to.
Cursor (.cursor/mcp.json)
{ "mcpServers": { "persuasion-taxonomy": { "url": "https://taxonomy.coppica.com/mcp" } } }VS Code (.vscode/mcp.json)
{ "servers": { "persuasion-taxonomy": { "type": "http", "url": "https://taxonomy.coppica.com/mcp" } } }Run it on your own machine (any client that launches local servers)
{ "mcpServers": { "persuasion-taxonomy": { "command": "npx", "args": ["-y", "@coppica/persuasion-mcp"] } } }Related MCP server: AAJ Marketing Engines
What your AI can do with it
You don't need to name the tools. Ask for what you want and a capable model reaches for the right one, and in testing it did so in all 16 realistic requests we tried, without being told the server existed.
When someone asks... | The tool that answers |
"Write me a landing page / ad / email / sales letter" |
|
"Is this good?", "Roast this", "What's wrong with this copy?" |
|
"My ad gets clicks but no sales" |
|
"Give me other ways to build trust", "Make this less generic" |
|
"What is this technique called?", "How does it work?" |
|
"Which of these headlines is best?" |
|
"Is this claim believable?", "Is this button any good?" |
|
"How long should I run this test?" |
|
"Did my test win?" |
|
It also offers four ready-made prompts (/roast, /brief, /why-not-converting and /next-test) and the nine questions as a resource you can read in full.
What it keeps
Nothing you send it. Your copy, your brief and your test numbers are used to answer that one request and then dropped. The hosted server logs which tool was called and when, and like any website, its host keeps ordinary request logs for a short time. The full policy is at taxonomy.coppica.com/privacy.
Where the techniques come from
Every technique is an entry in The Persuasion Taxonomy, a catalog of persuasion techniques documented from real ads, sales letters, emails and pages, with examples from the 1920s to now. The catalog is free under CC BY 4.0. Each technique comes with a link to its page, which shows the real examples behind the advice.
Develop
npm install
npm run build
npm run smoke # connects as a client over stdio and calls every tool
npm run smoke -- --http # the same, over Streamable HTTP
npm run voice # checks every model-facing string for machine tellsThe catalog in data/ is a snapshot. npm run export-data refreshes it, and it needs read access to Coppica's database, so outside contributors can work against the snapshot as it is.
The src/http.ts module exports handleMcpRequest(request), which takes a web-standard Request and returns a Response. That makes it easy to host anywhere that speaks fetch: a Next.js route, a Vercel or Cloudflare function, or plain Node 18 and up.
Voice
Every word the server shows a model reads the way a good direct-response writer would write it: plain words, full sentences that lead into each other, no em dashes, no shouted labels and no "it's not X, it's Y". That goes for the instructions, the tool descriptions, every line of output and every error message. A model picks up the voice of whatever it reads and passes it on to whoever it's writing for, so the tool has to model the writing it asks for. src/voice.ts turns the scorers' findings into plain sentences, and npm run voice keeps it honest.
License
The code is MIT. The catalog data in data/ is CC BY 4.0 and belongs to The Persuasion Taxonomy by Coppica.
About
Built by Coppica. This server knows how readers think. Coppica connects that same model of the reader to your live conversion data, so over time it learns which answers actually sell to your buyers.
Available Tools
9 toolscheck_headlinesCheck and compare headlines, hooks, and subject linesARead-onlyIdempotentInspect
Check headlines, email subject lines, ad openings, video hooks, social post openings and first lines, and compare options against each other. For each line it tells you whether the line does its job in that spot, meaning which of the nine reader questions it answers, and whether a competitor could send it unchanged. It also shows exactly what a reader sees before the cutoff, flags anything that fails outright, and brings in evidence from thousands of real headline tests. Then it tells you what each option is betting on and which two to test. Before you call it, list the reader questions each line answers and quote the exact words doing the work. Use it whenever you write headlines, hooks or subject lines, whenever you have to choose between them, and whenever someone asks "which one is best?" You won't get a score out of ten. Nobody can predict a winner from the words alone, and that includes this tool.
Inputs: slot (required), lines (required), brief, follows, +1 more.
check_marketing_claimsCheck marketing claims and CTAsARead-onlyIdempotentInspect
Check whether marketing claims and calls to action are specific enough to believe. It catches the vague superlative, like "the best" or "#1", that readers discount on sight. It catches promises with no proof behind them and results with no mechanism, and it flags the generic buttons everyone uses, like "Learn more" and "Get started". Then it tells you how to fix each one. Use it when you write or review claims like "results in days", "trusted by thousands" or "the #1 tool", and for any button text. For headlines, check_headlines does the full job.
Inputs: claims (required).
diagnose_marketing_copyDiagnose marketing copy (roast / review)ARead-onlyIdempotentInspect
Review, critique or roast any piece of marketing copy, whether it's an ad, a landing page, an email, a sales page, a social post or a script, and find out why it might not persuade. Before you call it, read the copy and label each line with the one reader question it mainly answers, quoting the words exactly. Those labels go in the moves array. You get back which of the nine questions the copy answers for its goal, which it answers weakly and which it skips, along with the biggest gap and what readers do when it is missing. It also checks the order, whether the answers agree with each other, and the craft, pointing to the exact words that read as machine-written, like em dashes, "it's not X, it's Y" lines and sentences that all run the same length. Then it checks the opening line and suggests techniques from the catalog to fill the gap. Use it before you show anyone a draft you wrote, and whenever someone asks "is this good?", "roast this", "what's wrong with this copy?" or "how do I make it better?"
Inputs: copy (required), goal (required), moves (required), format (required), +5 more.
explain_why_not_convertingExplain why marketing is not convertingARead-onlyIdempotentInspect
Work out why an ad, a landing page, an email or a whole funnel isn't converting. Start from what you can see. Maybe people don't click (a low CTR), or they click and bounce, or they read and don't buy. Maybe they abandon the checkout or the form, the leads never buy, customers buy once and leave, or emails don't get opened or get opened and nobody clicks. Whatever the symptom, you get back the reader questions most likely going unanswered, what to check in the copy first, and the problems copy can't fix that you should rule out, along with techniques to try and the test that would confirm the diagnosis. So use it whenever someone says their marketing "isn't working", "isn't converting" or "isn't selling", or asks why results dropped.
Inputs: symptom (required), format, details, category, +1 more.
find_persuasion_techniquesFind persuasion techniquesARead-onlyIdempotentInspect
Search the Persuasion Taxonomy, 766 named persuasion techniques documented from real advertising and organized by the nine reader questions they answer. Describe what you want the copy to do, like build trust without testimonials, create urgency without fake scarcity, handle a price objection, make an opening less generic, prove a claim or reframe a problem. It finds the techniques that do it. Each one comes with its name and ID, a one-line definition, a real example, how common it is in a category if you name one, and a link. So reach for it when a draft relies on the obvious move and you want a less expected one, or when someone asks for tactics, angles, hooks or ideas.
Inputs: query (required), limit, format, category, +1 more.
get_persuasion_techniqueGet a persuasion techniqueARead-onlyIdempotentInspect
Look up one persuasion technique by its ID (like PT-PRV-10000), its slug or its name. You get the full definition, why it works, when it lands and when it backfires, real examples from advertising, related and opposite techniques, and a link you can cite. Use it before you apply or recommend a technique so you get it right, and whenever someone asks what a tactic is called or how it works.
Inputs: id (required), category.
plan_ab_testPlan an A/B testARead-onlyIdempotentInspect
Plan an A/B test for marketing copy. Give it the current conversion rate, the smallest lift worth detecting and the daily traffic, and it tells you how many visitors each version needs and how many days to run. It also frames the test as two different answers to the same reader question, so the result teaches you something you can reuse, and not just that "B won". Use it when someone asks how long to run a test, how much traffic they need, whether a test is worth running, or what to test next.
Inputs: daily_visitors (required), minimum_detectable_lift_percent (required), baseline_conversion_rate_percent (required), power, +5 more.
plan_marketing_copyPlan marketing copy (the nine reader questions)ARead-onlyIdempotentInspect
Plan any piece of marketing copy before you write it, whether it's an ad, a landing page, a sales page or sales letter, an email, a subject line, a social post, a headline or a video script. Give it the goal, the reader and the offer, and it tells you which of the nine questions every reader silently asks this piece has to answer, which ones deserve the most words for this reader, and a few ways to answer each one, drawn from real advertising and linked to the Persuasion Taxonomy. One option is always the established move and the rest are less expected, because left to itself a model answers every question with the move everyone else makes, and readers have learned to skim past it. So call it before you draft, even when you're sure you know how to write the piece, and when the draft is done, check it with diagnose_marketing_copy.
Inputs: goal (required), offer (required), format (required), audience (required), +4 more.
read_ab_test_resultRead an A/B test resultARead-onlyIdempotentInspect
Read the result of an A/B test. You get each version's conversion rate and lift, whether the difference is statistically significant, the confidence interval, and the chance each version really beats the original. It also warns you about the things that make a test result lie. Those include too few conversions, traffic that didn't split the way it should (a sample ratio mismatch), stopping the moment it looked good, and testing too many versions at once. So use it whenever someone shares test numbers, or asks "did my test win?", "is this significant?", "which version won?" or "should I keep it running?"
Inputs: versions (required), question, confidence, intended_split.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Most tools have clearly distinct purposes, with plan/diagnose_marketing_copy forming a clean before/after pair and find/get_persuasion_technique acting as search vs. lookup. The main soft spot is overlap between diagnose_marketing_copy (review a draft) and explain_why_not_converting (troubleshoot conversion symptoms), though the descriptions do differentiate symptom-based funnel diagnosis from copy critique. check_headlines vs. check_marketing_claims is explicitly disambiguated in the text.
All nine tools follow a consistent snake_case verb_noun pattern (plan_marketing_copy, diagnose_marketing_copy, find_persuasion_techniques, get_persuasion_technique, check_headlines, check_marketing_claims, plan_ab_test, read_ab_test_result). explain_why_not_converting is the only slight deviation into a verb_phrase, but the convention is unmistakably consistent overall.
Nine tools is well-scoped for a persuasion-taxonomy server, with each tool earning its place: planning, diagnosis, technique discovery/lookup, headline and claim checks, and a two-step A/B test workflow. No redundancy or filler.
The surface covers the full persuasion lifecycle well: planning, diagnosing, technique research, copy-element checks, and A/B test planning plus result reading. Minor gap is there's no tool to actually draft or rewrite copy, though that may be intentionally left to the model.
Maintenance
Related MCP Connectors
Curated marketing libraries and ideation for your AI: 1,800+ award-winning campaigns and frameworks.
Audits AI-written marketing (copy, landing pages, ads, SEO) against real teardowns and benchmarks
Real-time Meta, Google, LinkedIn and TikTok ad library access for AI assistants. No API keys.
AI marketing agent and AI ad generator: 1340 tools, usable alone. No model markup on Starter and up.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables creators and marketers to generate viral social media hooks, format text into Twitter threads with proper character limits, and audit sales copy with actionable feedback on power words and CTAs.3ISC
- AlicenseAqualityBmaintenanceDeterministic marketing math for AI agents: 62 engines that compute LTV:CAC, CAC payback, pipeline coverage, A/B test significance, budget allocation, pricing and retention from your own numbers. Runs locally with Node 18+, makes no network calls and stores no data.51MIT
- AlicenseNot gradedqualityCmaintenanceEnables plain-language growth marketing maths — CAC, LTV, ROAS, PPC forecasts, budgets, CLV and ecommerce metrics — alongside SEO and AI-visibility checks such as robots.txt AI-crawler audits, JSON-LD schema and meta tag generation. It is free, read-only and needs no authentication or API key.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude to run nine marketing calculations on real public data — A/B test evaluation and planning, email campaign analysis, budget simulation and optimization, store sales breakdowns, RFM customer segmentation, lead funnel analysis, and multi-model attribution comparison. It connects without an account and returns a short summary plus structured numbers so decisions rest on computed results rather than guesses.MIT