craft-gtm-mcp
# @shashwatgtmalpha/craft-gtm-mcp v2.2.25
By Helix GTM Consulting (https://gtmhelix.com), built by Shashwat Ghosh, Co-Founder and Fractional CMO.
**CRAFT GTM Framework MCP Server**: a complete redesign with metric parsing, context-aware outputs, and a structured draft with placeholders where your inputs give no fact.
## Use it hosted (no install)
Add `https://craft-gtm.gtmhelix.com/mcp` to Claude or ChatGPT as a custom connector, or to Codex or Gemini CLI as an MCP server. It needs no sign-in and always runs the newest version (2.2.25). The same tools run as a free web app with a form per tool at https://craft-gtm.gtmhelix.com/, and the setup steps are at https://craft-gtm.gtmhelix.com/connect/.
The npm package below is an older version (2.0.1 on npm on 27 September 2026) until the next npm release. Use it only if you need a local stdio server.
## What's New in v2.0.0
This is a **major redesign** addressing all critical issues from v1.x:
| Issue | v1.x | v2.0.0 |
|-------|------|--------|
| PMF Scorecard | Blank `___` outputs | **Actually parses and scores your metrics** |
| Launch Commander | Same 12-week template for all | **Adapts to launch type, team size, budget** |
| Retention Playbook | Generic health scores | **Parses churn reasons, creates specific interventions** |
| Competitive Intel | `[Research]` placeholders | **Uses your competitor data, generates battle cards** |
| CRAFT Analyzer | Blank scorecard output | **Actually analyzes documents, finds gaps** |
## Installation
```bash
npm install -g @shashwatgtmalpha/craft-gtm-mcp
```
Or add to your Claude Desktop config:
```json
{
"mcpServers": {
"craft-gtm": {
"command": "npx",
"args": ["-y", "@shashwatgtmalpha/craft-gtm-mcp"]
}
}
}
```
## Tools and inputs
Tool names and input formats were checked against `tools/list` of craft-gtm-mcp 2.2.25 on 17 November 2026. Query `tools/list` for current descriptions.
| # | Tool | Title | What it does |
|---|---|---|---|
| 1 | `pmf_scorecard` | PMF Scorecard | Helps you decide whether you have product market fit and whether to scale: it takes your product, target market and current metrics (MRR, ACV, churn, NPS, CAC, LTV, retention, activation and similar) and returns a scorecard that scores each dimension against example benchmark ranges. It also gives priority actions and the data gaps to fill, reads the business model from your inputs, leaves the activation score out for services, connectivity and investment businesses, and quotes and answers your customer feedback. |
| 2 | `launch_commander` | Launch Commander | Helps you decide your launch plan: it takes what you are launching, the launch type, your target segments and your goals, and returns a phased launch plan with tasks, a messaging table and success metrics. Give a date for a dated timeline, or 'TBD' or a quarter such as 'Q2 2027' for a flexible plan. Tasks and messaging follow the sector and business model read from your inputs, and each goal is filed under its own metric. |
| 3 | `customer_interview_kit` | Customer Interview Kit | Helps you decide what to ask customers to test your hunch: it takes the interview type, the product context and the person you are interviewing, and returns an interview guide that fits the interview type, the sector and the product complexity. Questions use the sector's own language (the sector is chosen, or read from your inputs), your hypotheses are kept whole, and synthesis templates are included. |
| 4 | `retention_playbook` | Retention Playbook | Helps you decide why customers leave and what to do about each reason: it takes your customer segment, business model and current churn rate, and returns a retention playbook with health signals, interventions and an email draft for each churn reason. If you do not know why customers leave, leave the churn reasons out and you get a churn discovery kit instead. Your current interventions and data signals are used when you give them. |
| 5 | `partner_architect` | Partner Architect | Helps you decide what partner program to run and how to start it: it takes your company, product, partner model, partner goal and deal size, and returns a partner program with tiers, example commission amounts and KPIs. The structure differs for resellers, referrals, integrations, agencies, affiliates and white label, uses your existing partners when given, and names the partner types that fit your sector's buying committee. |
| 6 | `crisis_planner` | Crisis Planner | Helps you decide who does what when a crisis hits: it takes your company, industry, customer base and data sensitivity, and returns crisis playbooks with a response team and notification steps for each crisis. Name the crises you know of to get those playbooks; without them it uses a default set of common crises for your sector, not ranked by likelihood. Each compliance item you list is used in the notification steps. |
| 7 | `competitive_intel` | Competitive Intel | Helps you decide how to win against each competitor: it takes your product and the competitors you name, and returns one battle card per competitor built from your strengths, weaknesses, competitor details, objections, wins and losses. Each competitor detail goes to the competitor it names, each objection gets its own answer, and strengths and gaps taken from wins and losses stay in your own words. |
| 8 | `craft_gtm_analyzer` | CRAFT GTM Analyzer | Helps you decide whether a GTM plan is clear enough to run: it takes the text of a GTM document or plan and returns a score for each CRAFT dimension, based only on what the plan contains. Timeline counts real dates, durations and quarters; the answer shows the plan's own line for each dimension, names only the elements that are missing and suggests sections to add. |
| 9 | `scale_paid_check` | Scale Paid Check | Helps you decide whether to scale paid now: it takes your customer list (signing date, segment, monthly fee and any stop or return dates) and your churn reasons, and returns, for each customer group, scale, run a capped test, or hold, with the counts behind it, the stop rule, payback, a first draft response to each churn reason and a churn interview guide. |
### Inputs of each tool
#### 1. PMF Scorecard (`pmf_scorecard`)
| Input | Required | Type | Description |
|---|---|---|---|
| `product` | Yes | string | Product name and brief description |
| `target_market` | Yes | one of: `enterprise_saas`, `smb_saas`, `consumer`, `marketplace`, `fintech`, `logistics_tech`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Target market segment (e.g., 'Enterprise SaaS', 'SMB', 'Consumer') |
| `current_metrics` | Yes | string | Your current metrics (will be PARSED). Include any of: MRR, ARR, churn rate, NPS, CAC, LTV, retention rate, activation rate, DAU/MAU, trial conversion, revenue growth. Example: 'MRR: $50K, Churn: 3%, NPS: 45, CAC: $500, LTV: $3000, Retention: 92%' |
| `time_in_market` | No | one of: `pre_launch`, `0_6_months`, `6_12_months`, `1_2_years`, `2_plus_years` | How long the product has been in market (shown in the scorecard) |
| `customer_feedback` | No | string | Optional: Qualitative feedback themes (e.g., 'Users love X but struggle with Y') |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 2. Launch Commander (`launch_commander`)
| Input | Required | Type | Description |
|---|---|---|---|
| `product_feature` | Yes | string | What you're launching (product/feature name and description) |
| `launch_type` | Yes | one of: `major_release`, `feature_launch`, `beta_launch`, `product_update`, `market_expansion` | Type of launch determines plan complexity |
| `target_segments` | Yes | string | Target customer segments (comma-separated) |
| `goals` | Yes | string | Launch success metrics (e.g., '500 signups, $50k pipeline, 10% trial conversion, 1000 downloads') |
| `launch_date` | No | string | Target launch date. Accepts: 'YYYY-MM-DD', 'Q1 2027', 'March 2027', or 'TBD' for planning mode |
| `available_channels` | No | string | Optional: Marketing channels available (comma-separated). E.g., 'email, linkedin, blog, webinar, PR, paid_ads, community' |
| `team_size` | No | one of: `solo`, `small_2_5`, `medium_6_15`, `large_15_plus` | Marketing/GTM team size affects task distribution |
| `budget_level` | No | one of: `bootstrap`, `moderate`, `well_funded` | Budget affects recommended tactics |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 3. Customer Interview Kit (`customer_interview_kit`)
| Input | Required | Type | Description |
|---|---|---|---|
| `interview_type` | Yes | one of: `discovery`, `validation`, `feedback`, `churn`, `win_loss`, `persona_research` | Type of interview determines question focus |
| `product_context` | Yes | string | Product/service being researched |
| `target_persona` | Yes | string | Who you're interviewing (role/title) |
| `industry` | No | one of: `saas`, `fintech`, `logistics_tech`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `ecommerce`, `marketplace`, `enterprise_software`, `consumer`, `other` | Industry affects terminology and context |
| `product_complexity` | No | one of: `simple`, `moderate`, `complex`, `highly_technical` | Affects technical depth of questions |
| `key_hypotheses` | No | string | Optional: Hypotheses to validate during interview |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 4. Retention Playbook (`retention_playbook`)
| Input | Required | Type | Description |
|---|---|---|---|
| `customer_segment` | Yes | string | Customer segment to focus on |
| `business_model` | Yes | one of: `saas_subscription`, `usage_based`, `marketplace`, `transactional`, `freemium`, `enterprise_contract` | Business model affects health score weighting |
| `current_churn_rate` | Yes | string | Current churn rate (e.g., '5%' or '5% monthly') |
| `churn_reasons` | No | string | OPTIONAL: Known churn reasons (comma-separated). If you don't know, leave blank to get discovery mode with churn analysis framework |
| `available_data_signals` | No | string | What usage data you can track (comma-separated). E.g., 'login frequency, feature usage, support tickets, NPS responses' |
| `cs_team_size` | No | one of: `no_dedicated_cs`, `small_1_3`, `medium_4_10`, `large_10_plus` | CS team capacity affects intervention strategy |
| `current_interventions` | No | string | Optional: What retention tactics you already do |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 5. Partner Architect (`partner_architect`)
| Input | Required | Type | Description |
|---|---|---|---|
| `company` | Yes | string | Your company name |
| `product` | Yes | string | Product partners will sell/integrate |
| `partner_model` | Yes | one of: `reseller`, `referral`, `integration_tech`, `agency_si`, `affiliate`, `oem_white_label` | Partner type determines program structure |
| `partner_goals` | Yes | string | Revenue/growth targets from partners |
| `your_deal_size` | Yes | string | Average deal size as one amount (e.g., '$5000 ACV', '$5K' or '$500/month'; a range is refused). It scales the example commission amounts; the example rates are fixed |
| `partner_support_capacity` | No | one of: `minimal_self_serve`, `moderate`, `high_touch` | How much partner support can you provide? |
| `existing_partners` | No | string | Optional: Current partner types/count |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 6. Crisis Planner (`crisis_planner`)
| Input | Required | Type | Description |
|---|---|---|---|
| `company` | Yes | string | Company name |
| `industry` | Yes | one of: `fintech`, `saas`, `logistics_tech`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `ecommerce`, `enterprise`, `consumer`, `other` | Industry affects which crises to prioritize |
| `customer_base` | Yes | one of: `b2b_enterprise`, `b2b_smb`, `b2c_consumer`, `mixed` | Customer type affects communication approach |
| `data_sensitivity` | Yes | one of: `high_pii_financial`, `medium_business_data`, `low_general` | Data sensitivity affects security protocols |
| `potential_crises` | No | string | OPTIONAL: Crisis types to plan for (comma-separated). If not provided, the tool uses a default set of common crises for your industry (not ranked by likelihood). Options: data_breach, service_outage, pr_incident, executive_departure, security_vulnerability, regulatory_action, product_safety, customer_data_exposure |
| `company_size` | No | one of: `startup_under_50`, `scaleup_50_200`, `midsize_200_1000`, `enterprise_1000_plus` | Affects response team structure |
| `compliance_requirements` | No | string | Optional: Relevant compliance, comma-separated (for example ISO 27001, SOC 2, GDPR). Each item is named in the notification steps |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 7. Competitive Intel (`competitive_intel`)
| Input | Required | Type | Description |
|---|---|---|---|
| `your_product` | Yes | string | Your product name and brief description |
| `competitors` | Yes | string | Competitor names (comma-separated). Will generate battle card for EACH |
| `your_strengths` | No | string | OPTIONAL: What you do better (comma-separated). Will be DERIVED from wins/losses if not provided |
| `your_weaknesses` | No | string | OPTIONAL: Where competitors beat you (comma-separated). Will be DERIVED from wins/losses if not provided |
| `competitor_details` | No | string | Optional: Any known details about competitors. E.g., 'Competitor A is cheaper, Competitor B targets enterprise' |
| `common_objections` | No | string | Sales objections you hear (comma-separated). E.g., 'too expensive, missing X feature, competitor has better Y' |
| `recent_wins` | No | string | Why customers chose you over competitors: will be used to DERIVE strengths |
| `recent_losses` | No | string | Why you lost deals to competitors: will be used to DERIVE weaknesses |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 8. CRAFT GTM Analyzer (`craft_gtm_analyzer`)
| Input | Required | Type | Description |
|---|---|---|---|
| `document_content` | Yes | string | The GTM document/plan to analyze. Paste full content: it will be PARSED and EVALUATED |
| `document_type` | Yes | one of: `gtm_strategy`, `launch_plan`, `campaign_brief`, `quarterly_plan`, `project_proposal`, `marketing_plan` | Type of document (shown in the analysis) |
| `intended_audience` | No | string | Optional: Who will read/approve this document |
| `desired_outcome` | No | string | Optional: What action should this document drive |
| `your_sector` | No | one of: `logistics_tech`, `fintech`, `saas`, `vertical_saas`, `ai_native`, `ites`, `telecom`, `software`, `cybersecurity`, `other` | Optional: your company's own industry (not your customers'). When given, it decides the sector notes; when left out, the tool reads it from your words and stays neutral if they are unclear. |
#### 9. Scale Paid Check (`scale_paid_check`)
Answers "Should we scale paid now?" per customer group (`SCALE`, `CAPPED_TEST`, or `HOLD`) from a customer list, then chains `retention_playbook` and `customer_interview_kit`. Every date is computed from `as_of`, so identical inputs always produce identical outputs.
| Input | Required | Type | Description |
|---|---|---|---|
| `product` | Yes | string | Product in one line |
| `business_model` | Yes | one of: `saas_subscription`, `usage_based`, `marketplace`, `transactional`, `freemium`, `enterprise_contract`, `services_contract`, `connectivity_contract`, `investment_mandate` | Business model, passed on to `retention_playbook` |
| `billing_term` | Yes | one of: `monthly`, `annual` | How customers are billed |
| `as_of` | Yes | string (`YYYY-MM-DD`) | The date the list was pulled |
| `customers` | Yes | array (1 to 2000 objects) | Customer rows (`id`, `signed`, `segment`, `monthly_fee`, and optional `stopped`, `resumed`, `monthly_starts`) |
| `churn_reasons` | Yes | string | Reasons in customers' words, comma or line separated |
| `interview_persona` | Yes | string | Role to interview, for the interview kit |
| `metrics` | No | array of objects | Optional metrics (`name`, `value`, `counts`, `period`) |
| `stop_line` | No | number (default `0.80`) | Share of a cohort that must still pay at month 12 (Shashwat's example line for a $36,000 contract, not a benchmark) |
| `payback_line_months` | No | number (default `12`) | Longest acceptable paid payback in months (Shashwat's example line for a $36,000 contract, not a benchmark) |
| `gross_margin` | No | number (`0` to `1`) | Gross margin needed for the money section |
| `paid_cac` | No | number | Paid-only CAC |
| `blended_cac` | No | number | Blended CAC, shown for contrast only |
| `test_cap` | No | number | All-in budget for a capped test |
| `win_rate_floor` | No | number (`0` to `1`) | Win rate the buyer is confident paid can reach |
| `win_rate_target` | No | number (`0` to `1`) | Highest win rate the buyer would believe |
## Design Principles (v2.0)
1. **No blank `___` lines**: where your inputs give no fact, the output shows a placeholder in brackets to fill in
2. **Context-aware**: outputs adapt based on inputs provided
3. **Discovery mode**: if information is missing, tools ask questions to find it
4. **A structured draft with placeholders**: each tool returns a structured draft to edit, with placeholders where your inputs gave no fact
5. **Progressive enhancement**: more input gives a richer output
## Author
**Shashwat Ghosh**, Co-Founder and Fractional CMO, [Helix GTM Consulting](https://tools.gtmhelix.com), with 24+ years in B2B and 10+ years of fractional experience
## License
MIT
## Hosted connector (Streamable HTTP)
The same tools are also available as a hosted MCP server, so they work in Claude on the web, desktop and mobile without installing anything.
- Server URL: `https://craft-gtm.gtmhelix.com/mcp`
- Transport: Streamable HTTP (stateless, JSON responses). Authentication: none.
- Setup guide: https://craft-gtm.gtmhelix.com/connect/
- In Claude: Customize, then Connectors, then Add custom connector, and paste the server URL.
- In Claude Code: `claude mcp add --transport http craft-gtm https://craft-gtm.gtmhelix.com/mcp`
The npm package (stdio) and the hosted server run the same `createServer()` code in `src/server.ts`.
## Privacy Policy
Full policy: <https://craft-gtm.gtmhelix.com/privacy/> (also in [PRIVACY.md](PRIVACY.md)).
- **Data collection:** the hosted server receives only the tool name and the inputs of each tool call. The npm package runs on your computer and sends nothing to us.
- **Use and storage:** inputs are used only to build that call's reply. Inputs and answers are not stored: no database, no files, no cache, no logging of inputs or outputs by our code. Each call adds one anonymous usage record (date and time, site and tool name, app kind, web form or assistant); see the privacy page.
- **Third-party sharing:** none by us. Netlify hosts the server and processes requests under its own policy (https://www.netlify.com/privacy/). Fonts are served from this site, so loading a page contacts no one else.
- **Retention:** we keep no tool inputs or outputs. Netlify keeps its own platform logs under its policy.
- **Contact:** shashwat@gtmhelix.com
TDQS
Scored across 10 tools
Most tools have distinct GTM decision outputs, and several descriptions explicitly say when to use one instead of another overlapping tool. The main ambiguity is among scale_paid_check, pmf_scorecard, retention_playbook, and segment_and_seat_cut_check, which all touch growth/churn decisions, but their inputs and outputs are differentiated enough for an agent to select appropriately.
All tool names use consistent snake_case and compound descriptive names, which makes the set readable and predictable in style. The names are mostly artifact/function nouns rather than a strict verb_noun pattern, but the convention is internally consistent.
Ten tools is well within the appropriate range for a GTM advisory server. Each tool covers a distinct planning or decision area, and the count is neither bloated nor too thin.
The surface covers a broad GTM decision lifecycle: competitive intel, plan assessment, PMF, paid scaling, launch, interviews, retention, partners, crisis planning, and segment economics. There are minor adjacent gaps such as dedicated positioning/messaging or sales-enablement operations, but the core advisory workflows are well represented.