A
licenseA
qualityD
maintenanceValidates startup ideas with a deterministic scorecard, evidence brief, and verdict before code is written, integrating with MCP-aware build agents to avoid building dead-on-arrival products.
1
11 npm
MIT
marketing-scope-mcp
A campaign pre-flight server for AI agents: it plans marketing campaigns, scores offers explainably, builds a registry-backed plan, and gates every tactic before spend.
plan_campaign – Decompose a campaign objective into offer targets, channel targets, anti-targets (budget black holes), and kill criteria (optionally with audience hints).
score_offer – Grade one offer statement on an explainable 0–100 scale (clarity 20 / audience specificity 24 / differentiation 20 / proof & risk reversal 20 / CTA 16) with per-dimension evidence; grades A–D; caches scores in memory by exact text.
build_plan – Write a markdown campaign-plan shell (strategy stubs, channel briefs, numbered offer registry, scoring appendix) to
data/campaigns/and return the plan id; rejects any offer not previously scored, naming it.check_plan – Validate a plan read-only: every substantive tactic must cite a registry offer (
[O1]-style) and name a success metric; violations returned as an error list, never a silent pass.Runs as a local MCP server over stdio, Streamable HTTP (
/mcp), or Docker, with plans persisted on disk underMARKETING_SCOPE_DATA_DIR(default./data).
marketing-scope-mcp
Campaign pre-flight for AI agents. Plan the campaign, score the offers explainably, build a registry-backed plan, then verify every tactic cites a scored offer and names a success metric — before any money is spent.
The sibling of research-scope-mcp
(sources → citations) applied to marketing: tactics → scored offers.
The discipline
plan_campaign → score_offer → build_plan → check_plan
(strategy) (0–100) (shell) (gate)plan_campaign(objective)— decompose a marketing goal into offer targets, channel targets, anti-targets (budget black holes), and kill criteria. Kill criteria are hard stops, not suggestions.score_offer(offer)— one offer statement graded on an explainable 0–100 scale: clarity 20 / audience specificity 24 / differentiation 20 / proof & risk reversal 20 / call to action 16. Grades: A ≥ 80, B ≥ 65, C ≥ 45, D < 45. Every dimension returns with its evidence, so the number is auditable, not a vibe.build_plan(goal, offers[])— writes a campaign-plan shell (strategy, channel briefs, numbered offer registry, scoring appendix) and rejects any offer that was never scored, naming them.check_plan(plan_id | plan_path)— every tactic must cite a registry offer ([O1]-style) and name a success metric. Violations come back as an error list — never a silent pass.
Related MCP server: PrePilot MCP Server
Install
Node ≥ 20.
npm install -g marketing-scope-mcp
# or run from source:
git clone https://github.com/AxelVerneBooks/marketing-scope-mcp
cd marketing-scope-mcp && npm install && npm run buildClaude Code
claude mcp add marketing-scope -- node /path/to/dist/index.jsCursor (.cursor/mcp.json)
{ "mcpServers": { "marketing-scope": { "command": "node", "args": ["/path/to/dist/index.js"] } } }Streamable HTTP
node dist/index.js --http --port 3002 # serves MCP at http://127.0.0.1:3002/mcpDocker
docker build -t marketing-scope-mcp -f docker/Dockerfile .
docker run -d --name marketing-scope -p 3002:3002 marketing-scope-mcp
# MCP at http://127.0.0.1:3002/mcp; plans persist in the /app/data volumeData dir (plans on disk) defaults to ./data; override with
MARKETING_SCOPE_DATA_DIR.
Example session
> plan_campaign(objective: "sell 30 copies of the build manual in 30 days")
→ offer targets, channel targets, kill criteria incl.
"Every scored offer below 45/100 → STOP; rework before spending"
> score_offer(offer: "...12 print-ready farm ledgers only $19, includes
wall chart — unlike generic ledgers it strips to 40 records a season.
Start today.")
→ 88/100 (A), breakdown with per-dimension evidence
> build_plan(goal: ..., offers: [that exact text]) # unscored → hard error
> check_plan(...) # orphan tactics → error list; metric-less → flaggedLicense
MIT — see LICENSE.
Prefer it prebuilt? Campaign Pre-Flight Starter Kit — the built server plus one worked campaign run and the 4-step setup, $9, MIT, free lifetime updates. The one-page scoring rubric it enforces is free, no email wall. (Disclosure: I built and sell both; these are my links.)
Available Tools
4 toolsbuild_planBuild campaign-plan shellA
Build a campaign-plan shell from already-scored offers: strategy stubs, channel briefs, numbered offer registry, scoring appendix. Writes a markdown file under data/campaigns/ and returns the plan id plus the shell text. Do NOT call it before each offer has a score_offer — unscored offer texts are rejected with an error naming them. Sibling distinction: this creates the shell; check_plan later validates everything written against it.
Inputs: goal (required), offers (required).
check_planCheck plan tactic coverageARead-onlyIdempotent
Verify every substantive campaign tactic (a) cites at least one scored offer from the registry and (b) names a success metric. Violations are returned as an error list — never a silent pass. Read-only tool: inspects the registry and the plan file but writes nothing. Use it after every build_plan and again after any manual edit; do NOT use it on arbitrary markdown that never went through build_plan without first scoring its offers. Sibling distinction: build_plan creates the registry-backed shell; check_plan validates whatever is on disk against that registry.
Inputs: plan_id, plan_path.
plan_campaignPlan a campaignARead-onlyIdempotent
Turn a campaign objective into a pre-spend plan: offer targets, channel targets, anti-targets (budget black holes), and kill criteria. Purpose: decompose a marketing goal into scoreable tactics BEFORE any spend. Use this before score_offer on any new product/launch; re-plan only when kill criteria trigger. Sibling distinction: score_offer grades ONE offer statement; this plans the whole campaign strategy.
Inputs: objective (required), audience_hints.
score_offerScore an offerAIdempotent
Score one offer statement (the exact sentence a prospect would read) on an explainable 0–100 offer-strength scale: clarity 20 / audience specificity 24 / differentiation 20 / proof & risk reversal 20 / call to action 16. Grades: A >= 80, B >= 65, C >= 45, D < 45. Every dimension comes back WITH its evidence, so the number is auditable rather than a vibe. Side effect: the score is cached in an in-memory registry keyed by the exact offer text (lost on restart; re-score before finalizing a plan). Do NOT use it as a general copy critique — it grades offer statements, not landing pages. Sibling distinction: plan_campaign plans the strategy; this grades one sentence; build_plan consumes the scores.
Inputs: offer (required), audience.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4.6/5.0
Scored across 4 tools
Disambiguation5/5
Each tool has a clearly distinct purpose with explicit sibling distinctions: plan_campaign plans strategy, score_offer grades a single offer, build_plan constructs the plan shell, and check_plan validates. No overlapping purposes or ambiguous boundaries.
Naming Consistency5/5
All tool names follow a consistent snake_case verb_noun pattern: plan_campaign, score_offer, build_plan, check_plan. The convention is predictable and readable throughout.
Tool Count5/5
Four tools exactly cover the campaign planning workflow—plan, score, build, check—each earning its place without redundancy or bloat. The count matches the scope perfectly.
Completeness5/5
The tool set covers the full lifecycle from initial strategy planning through offer scoring, plan construction, and final validation against the registry. No obvious gaps for the stated marketing-scope domain; agents can complete the intended workflow end-to-end.
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues
Related MCP Connectors
Marketing MCP: social, email, SMS, CRM, paid ads, analytics. OAuth; confirm before send/spend.
Causal check on AI agent claims, from ad-spend/ROAS lift to any decision: pass, caution or hold.
Creative-intelligence MCP for campaign strategy, ad builds, QA, and reporting.
Pre-deploy governance for AI agents: posture scores, policies, budget cap checks, trust manifests.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI clients to compose and execute marketing campaigns by mapping free-form intent to a deterministic plan of over 1,000 production-tested skills, supporting multiple workflows across paid ads, SEO, content, and more.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to perform marketing operations like campaign management, content creation, and outreach, with a tiered approval model ensuring human oversight for consequential actions.MIT
- FlicenseNot gradedqualityDmaintenanceEnables to plan, write, illustrate, and voice a full marketing campaign through an MCP pipeline that generates copy, moodboards, voiceovers, and images with automated guardrails and budget controls.-