# io.github.shashwatgtm/craft-content-mcp (remote · craft-content.gtmhelix.com)

CRAFT Content: 8 B2B content tools by Helix GTM Consulting

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `craft-content.gtmhelix.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/craft-content.md), [page](https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/craft-content)
- npm · `@shashwatgtmalpha/craft-content-mcp`: 77/100, [markdown](https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/shashwatgtmalpha-craft-content-mcp.md), [page](https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/shashwatgtmalpha-craft-content-mcp)

## Channel facts

- Endpoint: `https://craft-content.gtmhelix.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.2.22`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3121 tokens (~390/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability check failed: schema churn in the 19 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.shashwatgtm/craft-content-mcp server?

io.github.shashwatgtm/craft-content-mcp is a hosted endpoint at https://craft-content.gtmhelix.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http shashwatgtm-craft-content-mcp 'https://craft-content.gtmhelix.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "shashwatgtm-craft-content-mcp": {
      "url": "https://craft-content.gtmhelix.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "shashwatgtm-craft-content-mcp": {
      "type": "http",
      "url": "https://craft-content.gtmhelix.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.shashwatgtm-craft-content-mcp]
url = "https://craft-content.gtmhelix.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "shashwatgtm-craft-content-mcp": {
      "type": "remote",
      "url": "https://craft-content.gtmhelix.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add shashwatgtm-craft-content-mcp --url 'https://craft-content.gtmhelix.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  shashwatgtm-craft-content-mcp:
    url: "https://craft-content.gtmhelix.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "shashwatgtm-craft-content-mcp": {
      "Transport": "http",
      "Url": "https://craft-content.gtmhelix.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add shashwatgtm-craft-content-mcp -t streamable-http -u 'https://craft-content.gtmhelix.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "shashwatgtm-craft-content-mcp": {
      "type": "http",
      "url": "https://craft-content.gtmhelix.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 54 to 57.

### 2026-11-03 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50.

### 2026-11-02 (score 78, 0)

- [security] Tool “case_study_generator” rewrote its description, which is the text the model reads
- [security] Tool “content_repurposer” rewrote its description, which is the text the model reads
- [security] Tool “newsletter_builder” rewrote its description, which is the text the model reads
- [security] Tool “testimonial_capture” rewrote its description, which is the text the model reads
- [security] Tool “thought_leadership_series” rewrote its description, which is the text the model reads
- [security] Tool “webinar_script” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 349 → 390
- [cosmetic] “case_study_generator” added an optional parameter “publication_approval”
- [cosmetic] “content_repurposer” added an optional parameter “publication_approval”
- [cosmetic] “newsletter_builder” added an optional parameter “publication_approval”
- [cosmetic] “testimonial_capture” added an optional parameter “customer_status”
- [cosmetic] “testimonial_capture” added an optional parameter “publication_approval”
- [cosmetic] “thought_leadership_series” added an optional parameter “publication_approval”
- [cosmetic] “webinar_script” added an optional parameter “publication_approval”

### 2026-10-31 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40.

### 2026-10-29 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 34.

### 2026-10-27 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 24 to 27.

### 2026-10-25 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20.

### 2026-10-23 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 14.

## MCP tools (8)

### `case_study_generator` (~420 tokens)

Case Study Generator

Builds a customer case study from the customer name, your product and the challenge, solution and results you give (mode full), or an interview kit for collecting them (mode discovery). Optional customer industry, quote, interview notes and business model fit the wording to the customer. Returns a headline, the story with each result you list, a customer quote, social and email copy and sector notes when the sector can be read from your text. A bracket marks anything you did not give. Ask whether written customer approval covers the exact material and intended use.

Input parameters:

- `business_model` (string): Optional: how you charge, so the advice fits it. If omitted, it is read from your text and the answer says how.
- `challenge` (string): The customer's challenge or problem (needed in full mode)
- `customer_industry` (string): The customer's industry, used for context
- `customer_name` (string, required): Customer or company name
- `customer_quote` (string): Optional: a direct quote from the customer
- `interview_notes` (string): Optional: raw interview notes or a transcript. In full mode they fill a missing challenge, solution or results; the answer says they were not used when you gave all three
- `mode` (string): full builds the case study and needs the challenge, solution and results; discovery returns interview questions for collecting them
- `publication_approval` (string): Optional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission.
- `results` (string): Measurable outcomes, one per line or per semicolon (needed in full mode)
- `solution` (string): How your product solved it (needed in full mode)
- `your_product` (string, required): Your product or service name
- `your_sector` (string): 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.

### `newsletter_builder` (~408 tokens)

Newsletter Builder

Writes a first draft of a newsletter issue from your topic and the action you want readers to take. Optional key points, audience segment, newsletter type, tone, earlier topics and your product fit it to the reader. Returns a subject line and preview, an opening, a short section for each key point, your own call to action as the button, A/B subject lines, alternative opening hooks and sector notes. Without key points it suggests some from the topic and sector. The draft uses only what you gave: it adds no statistic or customer story, and says what it did not get. Ask whether written customer approval covers the exact material and intended use.

Input parameters:

- `audience_segment` (string): Who the newsletter is for; sets tone and depth
- `cta_goal` (string, required): The action readers should take, in your own words (for example 'register for the webinar', 'book a call', 'read the guide'); it becomes the button
- `key_points` (string): Optional: key points to cover, one per line, per semicolon or comma-separated. If not provided, points are suggested from the topic and newsletter type
- `newsletter_type` (string): The kind of newsletter
- `previous_topics` (string): Optional: recent newsletter topics, to avoid repetition and suggest connections
- `publication_approval` (string): Optional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission.
- `tone` (string): The writing tone
- `topic` (string, required): The main topic or theme of the newsletter
- `your_product` (string): Optional: your product or service name, used in the answer. Without it the answer says so and shows a placeholder.
- `your_sector` (string): 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.

### `webinar_script` (~466 tokens)

Webinar Script

Writes a webinar run of show and a full spoken script from your topic, target audience and webinar type. Optional duration, key takeaways, speakers, polls, product mention level, your product and business model shape it. Returns the run of show, the script with the speaker lines and on-screen cues for each segment built from your takeaways and speakers, polls with answer options, anticipated questions with answers, a follow-up email sequence and sector notes. Without key takeaways it suggests them from the topic and type. The script uses only what you gave and says what it did not get. Ask whether written customer approval covers the exact material and intended use.

Input parameters:

- `business_model` (string): Optional: how you charge, so the advice fits it. If omitted, it is read from your text and the answer says how.
- `duration` (string): The webinar length
- `include_polls` (boolean): Include poll suggestions with answer options
- `key_takeaways` (string): Optional: what attendees should learn, one per line, per semicolon or comma-separated. If not provided, takeaways are suggested from the topic
- `product_mention_level` (string): Whether to add product tie-in placeholders to the script ('none' leaves them out)
- `publication_approval` (string): Optional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission.
- `speakers` (string): Optional: speakers as you want them listed. Separate speakers with semicolons or line breaks ('Name, Title; Name, Title'), or with commas if each is one phrase
- `target_audience` (string, required): Who will attend (for example 'Support leaders at consumer apps')
- `topic` (string, required): The webinar topic or title
- `webinar_type` (string, required): The kind of webinar; sets the structure
- `your_product` (string): Optional: your product or service name, used in the answer. Without it the answer says so and shows a placeholder.
- `your_sector` (string): 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.

### `content_repurposer` (~357 tokens)

Content Repurposer

Turns a source text into finished versions for other channels: a LinkedIn post, an X thread, an email, a blog summary and quote cards. Needs the source text and its type. Optional target formats, brand voice and a key message steer the result. Each version is written from whole sentences of your source, with key points chosen by a stated rule and kept in the source order; claims it cannot support are listed to source, and any requested format it does not know is named. Returns the versions, notes on the key points and proof used, and sector notes. Ask whether written customer approval covers the exact material and intended use.

Input parameters:

- `brand_voice` (string): The brand voice to keep
- `key_message` (string): Optional: the core message to emphasize in every format
- `publication_approval` (string): Optional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission.
- `source_content` (string, required): The original content to repurpose (a blog post, article or transcript, for example)
- `source_type` (string, required): The kind of content the source is
- `target_formats` (string): Optional: formats to generate, comma-separated. Defaults to: linkedin_post, twitter_thread, email, blog_summary, quote_cards. Other options: infographic_outline, video_script, podcast_talking_points,…
- `your_sector` (string): 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.

### `thought_leadership_series` (~415 tokens)

Thought Leadership Series

Writes a first draft of each article in a thought leadership series from your topic, your take and the reader you write for. Optional proof points, author background, number of articles and article style shape them. Returns, for each article, a headline, a short draft with the objection it answers, your proof and a way to test the idea, a promotional post for each article, a publishing order and sector notes. Your take and proof points are quoted as you wrote them and no result, customer or figure is invented. Without proof points it names the evidence to gather. Ask whether written customer approval covers the exact material and intended use.

Input parameters:

- `article_type` (string): The style of the articles
- `author_background` (string): Optional: your role and why you are credible (for example 'a long career in enterprise sales')
- `num_articles` (integer): How many articles to outline, a whole number from 1 to 5. If left out, the series has three articles
- `proof_points` (string): Optional: evidence supporting your take: personal stories, client examples, data or stats, one per line, per semicolon or comma-separated. If not provided, proof points to gather are suggested
- `publication_approval` (string): Optional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission.
- `target_reader` (string, required): Who should read this, named specifically (for example 'Heads of IT at companies with many branches' rather than 'managers')
- `topic` (string, required): The topic you want to build authority on
- `your_sector` (string): 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.
- `your_take` (string, required): Your own view on this topic: what you believe that others do not, or your contrarian view

### `testimonial_capture` (~408 tokens)

Testimonial Capture

Prepares a testimonial request from the customer's name, company, success story and the type of testimonial you want. Optional role, relationship, intended use, incentive, your product and business model fit it to the customer. Returns a request email, interview questions for the customer's role and sector, quote drafts for the customer to edit and a sign-off checklist. It uses your product name when you give it and says so when you do not. Ask whether written customer approval covers the exact material and intended use.

Input parameters:

- `business_model` (string): Optional: how you charge, so the advice fits it. If omitted, it is read from your text and the answer says how.
- `customer_company` (string, required): The customer's company
- `customer_name` (string, required): The customer's name
- `customer_role` (string): The customer's job title
- `customer_status` (string): Ask whether the customer is active or cancelled before a testimonial request. A confirmed typed fact takes precedence over cancellation wording.
- `incentive` (string): Optional: what you are offering in return
- `publication_approval` (string): Optional confirmed written approval for this exact customer name, figures, quote and intended use. Ask before publication. A draft cannot grant customer permission.
- `relationship_context` (string): How long they have been a customer and the key interactions
- `success_story` (string, required): A short description of their success with your product
- `testimonial_type` (string, required): The kind of testimonial you need
- `use_case` (string): Where the testimonial will be used (the website or a sales deck, for example)
- `your_product` (string): Optional: your product or service name, used in the answer. Without it the answer says so and shows a placeholder.
- `your_sector` (string): 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.

### `sales_enablement_content` (~371 tokens)

Sales Enablement Content

Builds a sales kit from your product, the persona you sell to and your proof points. Optional objections, value propositions, competitor objections, price context, sales stage and business model shape it. Returns a pitch order, a script for each objection answered with the sector's pattern and the proof point that fits it, competitor responses, discovery questions and follow-up templates. Without objections it suggests the ones your sector raises.

Input parameters:

- `business_model` (string): Optional: how you charge, so the advice fits it. If omitted, it is read from your text and the answer says how.
- `common_objections` (string): Optional: sales objections you hear, one per line, per semicolon or comma-separated. If not provided, likely objections for your sector are suggested
- `competitor_objections` (string): Optional: 'why not [competitor]' objections
- `price_context` (string): Optional: your pricing against the market (for example 'Premium, above market', 'Budget option' or 'Mid-market')
- `product` (string, required): The product name and what it does
- `proof_points` (string, required): Evidence for your claims: case studies, metrics and quotes, one per line, per semicolon or comma-separated
- `sales_stage` (string): The stage of the sales funnel
- `target_persona` (string, required): Who sales is pitching to (role and company type)
- `value_props` (string): Optional: key value propositions, one per line, per semicolon or comma-separated. Taken from the proof points if not provided
- `your_sector` (string): 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.

### `craft_content_improver` (~276 tokens)

CRAFT Content Improver

Reviews pasted copy and its content type against listed rules: buzzwords, claims that need proof, fragments, unfilled merge fields, claims about the reader and a missing figure or ask. Optional goal, audience and tone preference refine the review. Returns a score for each area with each deduction quoted from your text, and the edits it made. If it finds no edit to make, it says so and prints no improved version.

Input parameters:

- `audience` (string): Optional: who the content is for. The review reports when the text never mentions them
- `content` (string, required): The content to review
- `content_type` (string, required): The kind of content; it changes which checks apply
- `goal` (string): Optional: what the content should achieve (for example 'book a first meeting' or 'educate readers'). If not given, a goal is chosen from the content type
- `tone_preference` (string): The tone you want. Only more_formal and more_casual are checked in the text; any other value is named in the answer as not used
- `your_sector` (string): 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.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/craft-content#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 79
- 2026-11-03: 79
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 76
- 2026-10-27: 76
- 2026-10-26: 75
- 2026-10-25: 75
- 2026-10-24: 74
- 2026-10-23: 74
- 2026-10-22: 73
- 2026-10-21: 73
- 2026-10-20: 73
- 2026-10-19: 72
- 2026-10-18: 72
- 2026-10-17: 72

## Common questions

### What is the io.github.shashwatgtm/craft-content-mcp server?

io.github.shashwatgtm/craft-content-mcp is listed in the public MCP registry as io.github.shashwatgtm/craft-content-mcp. CRAFT Content: 8 B2B content tools by Helix GTM Consulting. This page covers its hosted endpoint (https://craft-content.gtmhelix.com/mcp).

### Is the io.github.shashwatgtm/craft-content-mcp server safe to use?

io.github.shashwatgtm/craft-content-mcp scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.shashwatgtm/craft-content-mcp server expose?

io.github.shashwatgtm/craft-content-mcp exposes 8 tools: case_study_generator, newsletter_builder, webinar_script, content_repurposer, thought_leadership_series, and 3 more. Their descriptions and schemas cost roughly 3,121 tokens of context every time the server is loaded.

### Does the io.github.shashwatgtm/craft-content-mcp server require authentication?

No. We connected to io.github.shashwatgtm/craft-content-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.shashwatgtm/craft-content-mcp server still maintained?

io.github.shashwatgtm/craft-content-mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://craft-content.gtmhelix.com/mcp
- Repository: https://github.com/shashwatgtm/craft-content-mcp
- Website: https://tools.gtmhelix.com/connectors/
- Changelog RSS feed: https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/craft-content.xml
- Changelog JSON feed: https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/craft-content.json
- HTML version of this page: https://verifymcp.io/servers/shashwatgtm-craft-content-mcp/craft-content