# Submitator (remote · mcp.submitator.com)

Launch your clients' products on up to 100 directories each from Claude, ChatGPT, Cursor or VS Code.

- Trust score: 83/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.submitator.com`: 83/100 (this document), [markdown](https://verifymcp.io/servers/com-submitator-mcp/mcp.md), [page](https://verifymcp.io/servers/com-submitator-mcp/mcp)
- npm · `submitator-mcp`: 74/100, [markdown](https://verifymcp.io/servers/com-submitator-mcp/submitator-mcp.md), [page](https://verifymcp.io/servers/com-submitator-mcp/submitator-mcp)

## Channel facts

- Endpoint: `https://mcp.submitator.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.1`

## 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**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - 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.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3157 tokens (~137/item across 23 items; 23 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 88% 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.
  - All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Submitator MCP server?

Submitator is a hosted endpoint at https://mcp.submitator.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-submitator-mcp 'https://mcp.submitator.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-submitator-mcp": {
      "url": "https://mcp.submitator.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-submitator-mcp]
url = "https://mcp.submitator.com/mcp"
```

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  com-submitator-mcp:
    url: "https://mcp.submitator.com/mcp"
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "com-submitator-mcp": {
      "type": "http",
      "url": "https://mcp.submitator.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.

### 2026-11-04 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 81, +14)

- [security improvement] Authorization: fail → pass
- [security] First check of Authorization: pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_events” rewrote its description, which is the text the model reads
- [security] Tool “list_projects” rewrote its description, which is the text the model reads
- [security] Tool “preview_launch” rewrote its description, which is the text the model reads
- [security] Tool “set_logo” rewrote its description, which is the text the model reads
- [security] Tool “update_project” rewrote its description, which is the text the model reads
- [security] Tool “whoami” rewrote its description, which is the text the model reads
- [security] Tool “verify_badge” rewrote its description, which is the text the model reads
- [security] Tool “add_directories” rewrote its description, which is the text the model reads
- [security] Tool “add_screenshot” rewrote its description, which is the text the model reads
- [security] Tool “create_report” rewrote its description, which is the text the model reads
- [security] Tool “get_badge” rewrote its description, which is the text the model reads
- [security] Tool “launch_project” rewrote its description, which is the text the model reads
- [security] Tool “update_project” is now declared destructive
- [security] Tool “add_directories” is now declared destructive
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.1.0 → 0.1.1
- [cosmetic] “launch_project” reworded the description of “excluded_directories”
- [cosmetic] “preview_launch” reworded the description of “excluded_directories”
- [cosmetic] “update_project” reworded the description of “competitors”
- [cosmetic] “update_project” reworded the description of “excluded_directories”
- [cosmetic] “add_directories” reworded the description of “excluded_directories”
- [cosmetic] “create_project” reworded the description of “competitors”
- [cosmetic] “create_project” reworded the description of “excluded_directories”

### 2026-10-30 (score 67)

First indexed and scored.

## MCP tools (23)

### `whoami` (~33 tokens)

Check the API key

Shows the agency and mode (live or test) behind the key, its permissions, launches left and the hourly request budget.

### `list_projects` (~98 tokens)

List client projects

Lists the agency projects, newest first. q finds one by part of its name or URL, and external_id by the agency's own id.

Input parameters:

- `cursor` (string): next_cursor from the previous page
- `external_id` (string)
- `limit` (integer): Rows to return, 20 by default, 50 at most
- `q` (string): Part of the name or URL
- `status` (string)

### `get_project` (~53 tokens)

Read a project

One project in full: status, what it waits for, progress counts, allowance, readiness, texts, images and the image candidates found on its site.

Input parameters:

- `project_id` (string, required): Project id (prj_...)

### `create_project` (~378 tokens)

Create a client project

Creates a project for a client's product from its URL. Name, tagline and description are filled from the site in the background when left out. Costs nothing: a launch is spent only by launch_project.

Input parameters:

- `audience` (object): Which audience-restricted directories fit the product
- `category`
- `competitors` (array): Up to 20, some directories need them. Replaces the whole list, so an entry left out is removed
- `contact_email`: Email the directories write to; required before launch
- `excluded_directories` (array): Directories never to use for this project. Replaces the whole list, which get_project shows; [] clears it
- `external_id`: The agency's own id for this client
- `launch_date`: YYYY-MM-DD
- `logo_url` (string): Public image URL for the logo (PNG, JPEG, GIF or WebP, 5 MB at most)
- `long_description`: Long description
- `maker_name`: Founder or maker name
- `metadata` (object): Up to 20 string pairs for the agency. Replaces all of it; {} clears it
- `name` (string): Product name; filled from the site when left out
- `price_amount_cents`: Price in cents
- `price_period`
- `pricing_model`
- `promo_code`: Discount code some directories ask for
- `promo_description`: What the promo code gives
- `screenshot_urls` (array): 1 to 5 public image URLs
- `short_description`: Short description
- `tagline`: One-line pitch
- `tags` (array): Up to 10. Replaces the whole list
- `twitter_url`: https://x.com/... profile
- `url` (string, required): The client product's public URL

### `update_project` (~354 tokens)

Update a project

Changes the project fields it is sent and leaves the others as they are; null clears a field, and a list replaces the whole list. contact_email cannot change after launch, and after launch an edit reaches only the listings that have not been sent to their directory.

Input parameters:

- `audience` (object): Which audience-restricted directories fit the product
- `category`
- `competitors` (array): Up to 20, some directories need them. Replaces the whole list, so an entry left out is removed
- `contact_email`: Email the directories write to; required before launch
- `excluded_directories` (array): Directories never to use for this project. Replaces the whole list, which get_project shows; [] clears it
- `external_id`: The agency's own id for this client
- `launch_date`: YYYY-MM-DD
- `long_description`: Long description
- `maker_name`: Founder or maker name
- `metadata` (object): Up to 20 string pairs for the agency. Replaces all of it; {} clears it
- `name` (string): Product name; filled from the site when left out
- `price_amount_cents`: Price in cents
- `price_period`
- `pricing_model`
- `project_id` (string, required): Project id (prj_...)
- `promo_code`: Discount code some directories ask for
- `promo_description`: What the promo code gives
- `short_description`: Short description
- `tagline`: One-line pitch
- `tags` (array): Up to 10. Replaces the whole list
- `twitter_url`: https://x.com/... profile
- `url` (string)

### `delete_draft` (~38 tokens)

Delete a draft project

Deletes a project that was never launched. A launched project cannot be deleted.

Input parameters:

- `project_id` (string, required): Project id (prj_...)

### `set_logo` (~71 tokens)

Set the logo

Sets or replaces a project's logo from a public image URL, fetched right away (a failed fetch answers image_unreachable).

Input parameters:

- `project_id` (string, required): Project id (prj_...)
- `url` (string, required): Public image URL: PNG, JPEG, GIF or WebP, 5 MB at most

### `add_screenshot` (~80 tokens)

Add a screenshot

Adds one screenshot to a project (5 at most), from a public image URL. Each call adds another one: a repeated call adds the same image twice.

Input parameters:

- `project_id` (string, required): Project id (prj_...)
- `url` (string, required): Public image URL: PNG, JPEG, GIF or WebP, 5 MB at most

### `remove_image` (~65 tokens)

Remove the logo or a screenshot

Removes the logo ("logo") or one screenshot (its img_ id). A launched project keeps at least its logo and one screenshot.

Input parameters:

- `image` (required): "logo", or the img_ id of a screenshot
- `project_id` (string, required): Project id (prj_...)

### `preview_launch` (~204 tokens)

Preview a launch

Free dry run of launch_project (or of add_directories on a launched project) with the same arguments: how many directories it would submit to, what is missing, what would unlock more and what it costs, plus the top and median DR of the auto pick. Its would_submit count is the confirm_selected that launch_project or add_directories requires for the same arguments.

Input parameters:

- `auto_replace` (boolean): true: within a day the free allowance fills up to 100 with fitting directories, replacing declined ones too. include turns it off unless you send true
- `directories`: "auto" (best matches, highest DR first), {include: [ids]} exactly these, or {exclude: [ids]} auto without these
- `excluded_directories` (array): Replaces the project's whole exclusion list for this request; [] clears it. directories: {exclude} leaves some out once instead
- `project_id` (string, required): Project id (prj_...)

### `find_directories` (~157 tokens)

Search the directory catalog

Searches the directories Submitator submits to, highest Domain Rating first, or reads one by id. Before the agency first buys launches, only the top 20 are shown.

Input parameters:

- `audience` (string)
- `cursor` (string): next_cursor from the previous page
- `directory_id` (string): Read this one directory; other filters are ignored
- `kind` (string): article = article platforms, open only through include
- `limit` (integer): Rows to return, 25 by default, 50 at most
- `min_dr` (integer): Lowest Domain Rating
- `q` (string): Part of the name
- `requires` (string): What the directory asks for
- `topic` (string)

### `project_directories` (~120 tokens)

A project's directory choices

Every catalog directory as seen by one project: suggested (the auto pick), open, locked (with what unlocks it), excluded or listed. Shows suggested, open and locked by default; the counts cover all.

Input parameters:

- `limit` (integer): Rows to return, 50 by default, 100 at most
- `offset` (integer): Rows to skip, for the next page
- `project_id` (string, required): Project id (prj_...)
- `states` (array): Which states to list; suggested, open and locked by default

### `launch_project` (~250 tokens)

Launch a project

Starts submissions and spends one of the agency's paid launches; with a sbm_test_ key it spends a test launch and submits nothing. Refuses unless confirm_selected equals the directory count preview_launch returns for the same arguments. With a live key, a client on MCP protocol 2026-07-28 that supports elicitation also gets a question to confirm, and the answer does not pass through the model. This remote server keeps no session, so a client on an earlier protocol version is not asked.

Input parameters:

- `auto_replace` (boolean): true: within a day the free allowance fills up to 100 with fitting directories, replacing declined ones too. include turns it off unless you send true
- `confirm_selected` (integer, required): The directory count from preview_launch that the user agreed to
- `directories`: "auto" (best matches, highest DR first), {include: [ids]} exactly these, or {exclude: [ids]} auto without these
- `excluded_directories` (array): Replaces the project's whole exclusion list for this request; [] clears it. directories: {exclude} leaves some out once instead
- `project_id` (string, required): Project id (prj_...)

### `add_directories` (~225 tokens)

Add directories to a launched project

Submits a launched project to more directories from its free allowance (no launch is spent). Refuses unless confirm_selected equals the directory count preview_launch returns for the same arguments. With a live key, a client on MCP protocol 2026-07-28 that supports elicitation also gets a question to confirm, and the answer does not pass through the model. This remote server keeps no session, so a client on an earlier protocol version is not asked. An include longer than the free allowance answers allowance_exhausted; a directory already listed answers invalid_directories.

Input parameters:

- `confirm_selected` (integer, required): The directory count from preview_launch that the user agreed to
- `directories` (required): "auto" (best matches, highest DR first), {include: [ids]} exactly these, or {exclude: [ids]} auto without these
- `excluded_directories` (array): Replaces the project's whole exclusion list for this request; [] clears it. directories: {exclude} leaves some out once instead
- `project_id` (string, required): Project id (prj_...)

### `list_listings` (~119 tokens)

List a project's listings

A project's listings, one per directory, highest DR first, with status and the live link once published. Or one listing in full by its id.

Input parameters:

- `cursor` (string): next_cursor from the previous page
- `directory` (string): Only the listing on this directory
- `limit` (integer): Rows to return, 25 by default, 50 at most
- `listing_id` (string): Read this one listing instead
- `project_id` (string): Project id (prj_...)
- `status` (string)

### `list_events` (~188 tokens)

What changed

Changes to projects and listings. The feed keeps 90 days and reads oldest first, so one call scans up to 1,000 events from the cursor (or from the start) and returns the newest ones since `since` (7 days ago by default). Passed back in a later call, its next_cursor reads only what came after. For the current state of a project, get_project and list_listings are cheaper.

Input parameters:

- `cursor` (string): next_cursor from an earlier call: continues from there
- `limit` (integer): Rows to return, 25 by default, 100 at most
- `project_id` (string): Only this project
- `since` (string): ISO time; 7 days ago by default, none when a cursor is given
- `type` (string): A type such as listing.live, or a group: listing.*, project.*, report.*

### `get_badge` (~82 tokens)

Get the badge install kit

The agency-branded badge some directories require on the client's site: its status, a message to forward to the client, the platforms it has install code for, and the code for the one named in platform.

Input parameters:

- `platform` (string): Platform name from the list, for its install code
- `project_id` (string, required): Project id (prj_...)

### `verify_badge` (~43 tokens)

Check the badge on the site

Checks the client's site for the badge now. Each project gets up to 10 checks an hour.

Input parameters:

- `project_id` (string, required): Project id (prj_...)

### `create_report` (~58 tokens)

Build a client report

Builds a PDF or XLSX report of a project, branded for the agency. Building takes a moment; get_report says when it is ready.

Input parameters:

- `format` (string, required)
- `project_id` (string, required): Project id (prj_...)

### `get_report` (~34 tokens)

Read a report

Whether a report is ready, and how to get the file.

Input parameters:

- `report_id` (string, required): Report id (rep_...)

### `get_share_link` (~44 tokens)

Read the client page link

The project's client page link (a read-only progress page in the agency's brand), with its views.

Input parameters:

- `project_id` (string, required): Project id (prj_...)

### `create_share_link` (~88 tokens)

Create the client page link

Gives the project's client page link. Returns the current link when there is one; replace: true issues a new link and turns the old one off.

Input parameters:

- `expires_at` (string): When the new link stops working
- `project_id` (string, required): Project id (prj_...)
- `replace` (boolean): Issue a new link even if one exists; the old one stops working

### `delete_share_link` (~38 tokens)

Turn the client page off

Turns the project's client page link off. Anyone holding it sees nothing afterwards.

Input parameters:

- `project_id` (string, required): Project id (prj_...)

## Diagnostics

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

## Score history

- 2026-11-05: 83
- 2026-11-04: 83
- 2026-11-03: 82
- 2026-11-02: 82
- 2026-11-01: 82
- 2026-10-31: 81
- 2026-10-30: 67

## Common questions

### What is the Submitator MCP server?

Submitator is an MCP server listed in the public MCP registry as com.submitator/mcp. Launch your clients' products on up to 100 directories each from Claude, ChatGPT, Cursor or VS Code. This page covers its hosted endpoint (https://mcp.submitator.com/mcp).

### Is the Submitator MCP server safe to use?

Submitator scores 83 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 Submitator MCP server expose?

Submitator exposes 23 tools: whoami, list_projects, get_project, create_project, update_project, and 18 more. Their descriptions and schemas cost roughly 2,820 tokens of context every time the server is loaded.

### Does the Submitator MCP server require authentication?

Yes. Submitator asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Submitator MCP server still maintained?

Submitator 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://mcp.submitator.com/mcp
- Authorisation metadata: https://mcp.submitator.com/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/submitator/submitator-mcp
- Website: https://submitator.com/white-label
- Changelog RSS feed: https://verifymcp.io/servers/com-submitator-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-submitator-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-submitator-mcp/mcp