# marketinque — launch plan & backlink index (remote · marketinque.com)

A 349-step SaaS launch plan and 958 backlink sources as tools an agent reads, acts on and records.

- Trust score: 71/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `marketinque.com`: 71/100 (this document), [markdown](https://verifymcp.io/servers/com-marketinque-launch-plan/marketinque.md), [page](https://verifymcp.io/servers/com-marketinque-launch-plan/marketinque)

## Channel facts

- Endpoint: `https://marketinque.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `36.0.0`

## 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 2026-09-28.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1597 tokens (~159/item across 10 items; 8 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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 10 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 marketinque — launch plan & backlink index MCP server?

marketinque — launch plan & backlink index is a hosted endpoint at https://marketinque.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 com-marketinque-launch-plan 'https://marketinque.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-marketinque-launch-plan": {
      "url": "https://marketinque.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-marketinque-launch-plan": {
      "type": "http",
      "url": "https://marketinque.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-marketinque-launch-plan]
url = "https://marketinque.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-marketinque-launch-plan": {
      "type": "remote",
      "url": "https://marketinque.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-marketinque-launch-plan --url 'https://marketinque.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-marketinque-launch-plan:
    url: "https://marketinque.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-marketinque-launch-plan": {
      "Transport": "http",
      "Url": "https://marketinque.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-marketinque-launch-plan -t streamable-http -u 'https://marketinque.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-marketinque-launch-plan": {
      "type": "http",
      "url": "https://marketinque.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.

### 2026-09-28 (score 71, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-26 (score 70, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Server version: 36.0.0 → 37.0.0

### 2026-09-25 (score 70, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 69, 0)

- [security] Tool “join_waitlist” rewrote its description, which is the text the model reads

### 2026-09-23 (score 69, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Server version: 35.0.0 → 36.0.0

### 2026-09-22 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_directory” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional] New prompt “intake”
- [functional] Server version: 22.0.0 → 35.0.0
- [cosmetic] “list_directories” reworded the description of “unrecorded_only”

### 2026-09-21 (score 68)

First indexed and scored.

## MCP tools (8)

### `whoami` (~30 tokens)

Who is calling

Which mode this connection is in — anonymous (read-only) or a project — and what that unlocks.

### `join_waitlist` (~135 tokens)

Ask for a marketinque project

Put the founder on the marketinque waitlist for a project (the idea queue, kit, dossier, signals, nightly routine — free for now, opening by waitlist). Call ONLY after the founder gave you their email and said yes in this session; `confirmed` attests that. One email, no spam; they can unsubscribe from any mail.

Input parameters:

- `confirmed` (boolean, required): True only if the founder explicitly agreed to join, in this session.
- `email` (string, required): The founder’s email, as they gave it.
- `product_url` (string): Their product, so the invitation can refer to it.

### `get_plan` (~242 tokens)

The launch plan

The launch plan. With no `node`: the outline — phases and objectives with step counts. With `node` (a phase or objective slug): every step under it, with status and whether it is unlocked. Anonymous callers pass `done`/`not_applicable`/`traits`; a project uses its own.

Input parameters:

- `done` (array): Step slugs already done — the "done" list of marketinque.json. Free tier only; a project's own ticks are used instead and this is ignored.
- `node` (string): A phase or objective slug from the outline, e.g. "p2" or "p2-dr-assets".
- `not_applicable` (array): Step slugs the founder ruled out — the "not_applicable" list of marketinque.json. Free tier only; ignored for a project.
- `traits` (array): Product traits that decide which steps apply (b2b, b2c, ai-native, dev-tool, no-code, mcp, has-integrations, eu-traffic, mobile-app); omit for the generic plan. Free tier only; a project's saved trai…

### `get_step` (~294 tokens)

One step in full

One plan step in full: title, detail, the target URL where it happens, the play it follows, the prerequisite slugs and whether they are met (unlocked), how it verifies (self, evidence URL or an automatic signal), minutes and cost, and founder_steps when part of the step is the founder’s own (an account, a handle): the exact page and what to do there, to hand over rather than do. Read it before working a step that next_steps or get_plan returned; the slug comes from those. Read-only; no side effects.

Input parameters:

- `done` (array): Step slugs already done — the "done" list of marketinque.json. Free tier only; a project's own ticks are used instead and this is ignored.
- `not_applicable` (array): Step slugs the founder ruled out — the "not_applicable" list of marketinque.json. Free tier only; ignored for a project.
- `slug` (string, required): The step slug exactly as get_plan or next_steps returned it, e.g. "p2-dest-alternatives".
- `traits` (array): Product traits that decide which steps apply (b2b, b2c, ai-native, dev-tool, no-code, mcp, has-integrations, eu-traffic, mobile-app); omit for the generic plan. Free tier only; a project's saved trai…

### `next_steps` (~267 tokens)

What to do next

The next unlocked, unstarted steps in tree order, and a sprint packed into `minutes`. Anonymous callers pass `done`/`not_applicable` (from marketinque.json) and `traits`; a project uses its own.

Input parameters:

- `checkable_only` (boolean): Only steps with a target to record or an automatic check.
- `done` (array): Step slugs already done — the "done" list of marketinque.json. Free tier only; a project's own ticks are used instead and this is ignored.
- `free_only` (boolean): Only steps that cost nothing.
- `limit` (integer): How many next steps to list (default 8).
- `minutes` (integer): Time available now; the sprint is packed into it (default 120).
- `not_applicable` (array): Step slugs the founder ruled out — the "not_applicable" list of marketinque.json. Free tier only; ignored for a project.
- `traits` (array): Product traits that decide which steps apply (b2b, b2c, ai-native, dev-tool, no-code, mcp, has-integrations, eu-traffic, mobile-app); omit for the generic plan. Free tier only; a project's saved trai…

### `list_directories` (~210 tokens)

Directories to submit to

Places that give a startup a backlink, one phase at a time in the order that works. Default phase bl-sprint: the 95 free, dofollow, page-scoped, graded rows. Each row carries its submission page (or where to find it) and, for a project, the listing already recorded.

Input parameters:

- `category` (string): Filter by the catalog category, e.g. "AI Tools", "Software Reviews".
- `limit` (integer): Default 25.
- `min_dr` (integer): Only rows with at least this domain rating (0–100).
- `offset` (integer): Rows to skip, for paging past `limit`.
- `phase` (string): bl-sprint (default) · bl-reach (free, nofollow/host-scoped) · bl-paid · bl-optional · bl-tail
- `unrecorded_only` (boolean): Project only: skip rows already recorded — listed, submitted or skipped. The next batch, in one call.

### `get_directory` (~121 tokens)

One directory

One directory from the index: domain rating, dofollow, price, category, the submission page URL (or where to look for it), account_required (the page redirected to a sign-in when probed — most rows want a sign-in at submit anyway), founder_fills (a form an agent cannot drive), the note from the last session that worked it, and — for a project — the outcome already recorded. Read the note before opening the page. Read-only.

Input parameters:

- `slug` (string, required): The catalog slug, e.g. "saashub".

### `get_submission_kit` (~51 tokens)

The submission kit

What every directory form asks for, written once. A project returns its product profile and brand dossier plus the state of the five kit steps; anonymous callers get the five steps to draft from the product site.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-marketinque-launch-plan/marketinque#diagnostics

## Score history

- 2026-09-28: 71
- 2026-09-27: 71
- 2026-09-26: 70
- 2026-09-25: 70
- 2026-09-24: 69
- 2026-09-23: 69
- 2026-09-22: 68
- 2026-09-21: 68

## Common questions

### What is the marketinque — launch plan & backlink index MCP server?

marketinque — launch plan & backlink index is an MCP server listed in the public MCP registry as com.marketinque/launch-plan. A 349-step SaaS launch plan and 958 backlink sources as tools an agent reads, acts on and records. This page covers its hosted endpoint (https://marketinque.com/mcp).

### Is the marketinque — launch plan & backlink index MCP server safe to use?

marketinque — launch plan & backlink index scores 71 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 marketinque — launch plan & backlink index MCP server expose?

marketinque — launch plan & backlink index exposes 8 tools: whoami, join_waitlist, get_plan, get_step, next_steps, and 3 more. Their descriptions and schemas cost roughly 1,350 tokens of context every time the server is loaded.

### Does the marketinque — launch plan & backlink index MCP server require authentication?

No. We connected to marketinque — launch plan & backlink index without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the marketinque — launch plan & backlink index MCP server still maintained?

marketinque — launch plan & backlink index is still listed as active in the MCP registry. We last reached this channel on 28 September 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://marketinque.com/mcp
- Repository: https://github.com/zeshutmax/demand-gen
- Website: https://marketinque.com/mcp-for-marketing
- Changelog RSS feed: https://verifymcp.io/servers/com-marketinque-launch-plan/marketinque.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-marketinque-launch-plan/marketinque.json
- HTML version of this page: https://verifymcp.io/servers/com-marketinque-launch-plan/marketinque