Skip to content

craft-gtm-mcp server

io.github.shashwatgtm/craft-gtm-mcpshashwatgtmstreamable-httpv2.2.23Scanned

CRAFT GTM: 8 go to market strategy tools by Helix GTM Consulting

10 tools: 10 change things.

Tools: 0 delete, 0 irreversible, 10 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

10 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the craft-gtm-mcp server can do

The craft-gtm-mcp server is published by the GitHub account shashwatgtm. It has 10 tools. It can create or change data (10 tools: pmf_scorecard, launch_commander, customer_interview_kit, retention_playbook and 6 more), but cannot delete data. None of its tools only reads.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 2.2.23.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

10 tools

Changes things 10Claude Code: ask
  • competitive_intelHelps 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, weakn…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of competitive_trap_setter when you need complete battle cards across the competitors you supply.

    Annotations the server declares

    • title: Competitive Intel
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • craft_gtm_analyzerHelps 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 co…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of launch_commander when you already have a GTM document to assess against CRAFT.

    Annotations the server declares

    • title: CRAFT GTM Analyzer
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • crisis_plannerHelps 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 notifi…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of retention_playbook when you need response roles and notification steps for operational crises.

    Annotations the server declares

    • title: Crisis Planner
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • customer_interview_kitHelps 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…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of icp_interview_synthesizer when you need questions and synthesis templates before conducting interviews.

    Annotations the server declares

    • title: Customer Interview Kit
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • launch_commanderHelps 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 t…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of craft_gtm_analyzer when you need to create a launch plan from a product, segments and goals.

    Annotations the server declares

    • title: Launch Commander
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • partner_architectHelps 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 tier…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of launch_commander when you need a partner program with tiers, commissions and KPIs.

    Annotations the server declares

    • title: Partner Architect
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • pmf_scorecardHelps 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, acti…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of scale_paid_check when you need a broad PMF assessment against the tool's example benchmarks.

    Annotations the server declares

    • title: PMF Scorecard
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • retention_playbookHelps 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 …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of scale_paid_check when you need interventions and email drafts for supplied churn reasons.

    Annotations the server declares

    • title: Retention Playbook
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • scale_paid_checkHelps 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 e…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of pmf_scorecard when you need a paid-growth decision grounded in customer cohorts and unit economics.

    Annotations the server declares

    • title: Scale Paid Check
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • segment_and_seat_cut_checkHelps you decide which customer segment to back, and whether your pricing is safe if AI cuts seats: it takes each segment's ACV, sales cycle, accounts, deal source and CAC, its log…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Helps you decide which customer segment to back, and whether your pricing is safe if AI cuts seats: it takes each segment's ACV, sales cycle, accounts, deal source and CAC, its logo, gross and net retention, how you charge in your own words, and your seller ramp, cost and qualified demand, and returns one page per segment with payback, gross profit per dollar of CAC, seller capacity after ramp and cycle, and the renewal if customers cut a share of seats. Ask the person to confirm the segment split, their own win rate and what customers can cut before marking each as confirmed; anything not confirmed or not given is shown as missing, never guessed. Read-only for business data. It needs no sign-in and stores no inputs or outputs. Hosted usage metadata is recorded. Missing required fields or invalid values return an error naming what to supply or correct. Use this instead of scale_paid_check when you need segment economics, seller capacity and seat-reduction scenarios.

    Annotations the server declares

    • title: Segment and Seat Cut Check
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:10 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
10
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 10 tools that change things (10 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://craft-gtm.gtmhelix.com/mcp: tools/list returned 10 tools to an anonymous client, including pmf_scorecard (write), launch_commander (write), customer_interview_kit (write), retention_playbook (write), partner_architect (write) and 5 more

    What this check looks for

Posture changes

  1. Nov 13, 2026
    • Tools that change things, listed without credentials: 8 to 10

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 added, 8 changed.+2 added~8 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 8 -> 10.View diff
    • Tools that change things, listed without credentials: 8 to 10
  3. Tools8 changed.~8 changedView diff

Install

Pinned to version 2.2.23. Values in angle brackets are yours to fill in.

claude mcp add --transport http craft-gtm https://craft-gtm.gtmhelix.com/mcp
claude mcp add --transport http craft-gtm https://craft-gtm.gtmhelix.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__craft-gtm__pmf_scorecard",
      "mcp__craft-gtm__launch_commander",
      "mcp__craft-gtm__customer_interview_kit",
      "mcp__craft-gtm__retention_playbook",
      "mcp__craft-gtm__partner_architect",
      "mcp__craft-gtm__crisis_planner",
      "mcp__craft-gtm__competitive_intel",
      "mcp__craft-gtm__craft_gtm_analyzer",
      "mcp__craft-gtm__scale_paid_check",
      "mcp__craft-gtm__segment_and_seat_cut_check"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as craft-gtm. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.shashwatgtm/craft-gtm-mcp/verify?hash=2e98683b72773bc6df417a88415170cf5c50a506049a208c2678e188c19f5be0" | jq -e '.changed == false'

Pinned hash 2e98683b7277, from Nov 20, 2026, 12:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.shashwatgtm/craft-gtm-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.shashwatgtm/craft-gtm-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.shashwatgtm/craft-gtm-mcp.svg)](https://radar.anlyon.com/servers/io.github.shashwatgtm/craft-gtm-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:49 UTC.

craft-gtm-mcp server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the craft-gtm-mcp server safe?

No scan can promise that. What its definitions show: 10 tools, 10 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the craft-gtm-mcp server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the craft-gtm-mcp server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the craft-gtm-mcp server have?

10 tools: 10 write. pmf_scorecard, launch_commander, customer_interview_kit, retention_playbook, partner_architect, crisis_planner, competitive_intel, craft_gtm_analyzer and 2 more.

Does the craft-gtm-mcp server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the craft-gtm-mcp server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the craft-gtm-mcp server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.