Submitator MCP server
com.submitator/mcpsubmitator.comstreamable-httpv0.1.4Scanned
Launch your clients' products on up to 110 directories each from Claude, ChatGPT, Cursor or VS Code.
23 tools: 8 can delete or cancel things, 5 change things and 10 only read.
- Reads private data · 5
- Reads text others write · 8
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
8 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 Submitator MCP server can do
The Submitator MCP server is published by submitator.com, a domain the MCP Registry verified. It has 23 tools. It can delete or cancel things (8 tools: update_project, delete_draft, set_logo, remove_image and 4 more) and create or change data (5 tools: create_project, add_screenshot, project_directories, verify_badge and 1 more). 10 tools only read.
5 tools read private data (preview_launch, find_directories, list_listings and 2 more); 8 tools bring in text other people can write (create_project, update_project, set_logo and 5 more); 2 tools can send data out of your system (create_project and add_screenshot). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way 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 3 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 0.1.4.
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.
23 tools
Deletes or cancels 8Claude Code: deny
add_directoriesSubmits a launched project to more directories from its free allowance (no launch is spent).Reads text others writeNo findings
Why it is in this group
- The name "add_directories" says "add": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Add directories to a launched project
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
delete_draftDeletes a project that was never launched.No findings
Why it is in this group
- The name "delete_draft" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Deletes a project that was never launched. A launched project cannot be deleted.
Annotations the server declares
- title: Delete a draft project
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
launch_projectStarts submissions and spends one of the agency's paid launches; with a sbm_test_ key it spends a test launch and submits nothing.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "start": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Launch a project
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
remove_imageRemoves the logo ("logo") or one screenshot (its img_ id).No findings
Why it is in this group
- The name "remove_image" says "remove": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Removes the logo ("logo") or one screenshot (its img_ id). A launched project keeps at least its logo and one screenshot.
Annotations the server declares
- title: Remove the logo or a screenshot
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
set_logoSets or replaces a project's logo from a public image URL, fetched right away (a failed fetch answers image_unreachable).Reads text others writeNo findings
Why it is in this group
- The name "set_logo" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Sets or replaces a project's logo from a public image URL, fetched right away (a failed fetch answers image_unreachable).
Annotations the server declares
- title: Set the logo
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
update_projectChanges the project fields it is sent and leaves the others as they are; null clears a field, and a list replaces the whole list.Reads text others writeNo findings
Why it is in this group
- The name "update_project" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Update a project
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
Changes things 5Claude Code: ask
add_screenshotAdds one screenshot to a project (5 at most), from a public image URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "add_screenshot" says "add": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- title: Add a screenshot
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_projectCreates a project for a client's product from its URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "create_project" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Annotations the server declares
- title: Create a client project
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_reportBuilds a PDF or XLSX report of a project, branded for the agency.No findings
Why it is in this group
- The name "create_report" says "create": a word for a change.
Description, as the server wrote it Builds a PDF or XLSX report of a project, branded for the agency. Building takes a moment; get_report says when it is ready.
Annotations the server declares
- title: Build a client report
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
project_directoriesEvery catalog directory as seen by one project: suggested (the auto pick), open, locked (with why, and what to change if the project can open it), excluded or listed.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 Every catalog directory as seen by one project: suggested (the auto pick), open, locked (with why, and what to change if the project can open it), excluded or listed. Shows suggested, open and locked by default; the counts cover all.
Annotations the server declares
- title: A project's directory choices
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
verify_badgeChecks the client's site for the badge now.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Checks the client's site for the badge now. Each project gets up to 10 checks an hour.
Annotations the server declares
- title: Check the badge on the site
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 10Show 10 read-only tools
find_directoriesSearches the directories Submitator submits to, highest Domain Rating first, or reads one by id.Reads private dataNo findings
Why it is in this group
- The name "find_directories" says "find": a word for reading.
What it can reach
- private-dataThe name "find_directories" says "find" and "directory": it reads files.
- private-dataThe description's first sentence says "search" and "directory": it reads files.
- private-dataThe input names a directory (input.directory_id), and the tool reads: it reads files.
Description, as the server wrote it 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.
Annotations the server declares
- title: Search the directory catalog
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_badgeThe 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 …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_badge" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "directory": it reads files.
- untrusted-inputThe description's first sentence says "message": it reads messages, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get the badge install kit
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_projectOne project in full: status, what it waits for, progress counts, allowance, readiness, texts, images and the image candidates found on its site.No findings
Why it is in this group
- The name "get_project" says "get": a word for reading.
Description, as the server wrote it One project in full: status, what it waits for, progress counts, allowance, readiness, texts, images and the image candidates found on its site.
Annotations the server declares
- title: Read a project
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_reportWhether a report is ready, and how to get the file.Reads private dataNo findings
Why it is in this group
- The name "get_report" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
Description, as the server wrote it Whether a report is ready, and how to get the file.
Annotations the server declares
- title: Read a report
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_eventsChanges to projects and listings.No findings
Why it is in this group
- The name "list_events" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: What changed
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_listingsA project's listings, one per directory, highest DR first, with status and the live link once published.Reads private dataNo findings
Why it is in this group
- The name "list_listings" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "directory": it reads files.
- private-dataThe input names a directory (input.directory), and the tool reads: it reads files.
Description, as the server wrote it 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.
Annotations the server declares
- title: List a project's listings
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_projectsLists the agency projects, newest first.No findings
Why it is in this group
- The name "list_projects" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: List client projects
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
preview_launchFree 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 mo…Reads private dataNo findings
Why it is in this group
- The name "preview_launch" says "preview": a word for reading.
What it can reach
- private-dataThe description's first sentence says "directory": it reads files.
- private-dataThe input names a directory (input.directories), and the tool reads: it reads files.
Description, as the server wrote it 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.
Annotations the server declares
- title: Preview a launch
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
whoamiShows the agency and mode (live or test) behind the key, its permissions, launches left and the hourly request budget.No findings
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
Description, as the server wrote it Shows the agency and mode (live or test) behind the key, its permissions, launches left and the hourly request budget.
Annotations the server declares
- title: Check the API key
- 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.
80 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data5
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__submitator__add_screenshot",
"mcp__submitator__create_project"
]
}
}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.
Looked at Nov 21, 2026, 19:23 UTC, unchanged since Nov 7, 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
- 13
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.submitator.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.submitator.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 13 tools that change things (8 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.submitator.com/mcp: tools/list returned 23 tools to an anonymous client, including update_project (destructive), delete_draft (destructive), set_logo (destructive), remove_image (destructive), launch_project (destructive) and 8 more
Posture changes
- Nov 7, 2026
- RFC 9728 protected resource metadata: none to https://mcp.submitator.com/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://api.submitator.com
- Dynamic client registration: not observed to no
- Client ID metadata documents: not observed to yes
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.
Tools3 changed.~3 changedView diff
- Changed:add_directoriesDeletes or cancelsinputSchema
- Changed:launch_projectDeletes or cancelsinputSchema
- Changed:preview_launchOnly readsinputSchema
Tools1 changed.~1 changedView diff
- Changed:project_directoriesChanges thingsdescription
PostureRemote posture changed. RFC 9728 protected resource metadata: none -> https://mcp.submitator.com/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://api.submitator.com; Dynamic client registration: not observed …View diff
- RFC 9728 protected resource metadata: none to https://mcp.submitator.com/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://api.submitator.com
- Dynamic client registration: not observed to no
- Client ID metadata documents: not observed to yes
Tools19 changed.~19 changedView diff
- Changed:add_directoriesDeletes or cancelsdescriptioninputSchemaannotations
- Changed:add_screenshotChanges thingsdescription
- Changed:create_projectChanges thingsinputSchema
- Changed:create_reportChanges thingsdescription
- Changed:find_directoriesOnly readsannotations
- Changed:get_badgeOnly readsdescriptionannotations
- Changed:get_projectOnly readsannotations
- Changed:get_reportOnly readsannotations
- Changed:get_share_linkOnly readsannotations
- Changed:launch_projectDeletes or cancelsdescriptioninputSchema
- Changed:list_eventsOnly readsdescriptionannotations
- Changed:list_listingsOnly readsannotations
- Changed:list_projectsOnly readsdescriptionannotations
- Changed:preview_launchOnly readsdescriptioninputSchemaannotations
- Changed:project_directoriesChanges thingsannotations
- Changed:set_logoDeletes or cancelsdescription
- Changed:update_projectDeletes or cancelsdescriptioninputSchemaannotations
- Changed:verify_badgeChanges thingsdescription
- Changed:whoamiOnly readsdescriptionannotations
Install
Pinned to version 0.1.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http submitator https://mcp.submitator.com/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http submitator https://mcp.submitator.com/mcp --header 'Authorization: <your-authorization>'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.
{
"permissions": {
"allow": [
"mcp__submitator__whoami",
"mcp__submitator__list_projects",
"mcp__submitator__get_project",
"mcp__submitator__preview_launch",
"mcp__submitator__find_directories",
"mcp__submitator__list_listings",
"mcp__submitator__list_events",
"mcp__submitator__get_badge",
"mcp__submitator__get_report",
"mcp__submitator__get_share_link"
],
"ask": [
"mcp__submitator__create_project",
"mcp__submitator__add_screenshot",
"mcp__submitator__project_directories",
"mcp__submitator__verify_badge",
"mcp__submitator__create_report"
],
"deny": [
"mcp__submitator__update_project",
"mcp__submitator__delete_draft",
"mcp__submitator__set_logo",
"mcp__submitator__remove_image",
"mcp__submitator__launch_project",
"mcp__submitator__add_directories",
"mcp__submitator__create_share_link",
"mcp__submitator__delete_share_link"
]
}
}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 submitator. Review it before you use it.
Capability tags behind 12 rules
- mcp__submitator__create_project untrusted-input, outbound
- mcp__submitator__update_project untrusted-input
- mcp__submitator__set_logo untrusted-input
- mcp__submitator__add_screenshot untrusted-input, outbound
- mcp__submitator__preview_launch private-data
- mcp__submitator__find_directories private-data
- mcp__submitator__launch_project untrusted-input
- mcp__submitator__add_directories untrusted-input
- mcp__submitator__list_listings private-data
- mcp__submitator__get_badge private-data, untrusted-input
- mcp__submitator__verify_badge untrusted-input
- mcp__submitator__get_report private-data
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/com.submitator/mcp/verify?hash=279b06416bebdb6c92091645d33f0257f67e5cb5a361ee62a6630a996a98950d" | jq -e '.changed == false'Pinned hash 279b06416beb, from Nov 15, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.submitator/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.submitator/mcp)Source: MCP Registry · repository. Synced Nov 15, 2026, 20:17 UTC.
Submitator MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Submitator MCP server safe?
- No scan can promise that. What its definitions show: 23 tools, 13 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 Submitator MCP server delete data?
- Yes. 8 tools can delete, cancel or revoke something: update_project, delete_draft, set_logo, remove_image, launch_project, add_directories and 2 more.
Can the Submitator 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 Submitator MCP server have?
- 23 tools: 8 destructive, 5 write, 10 read. update_project, delete_draft, set_logo, remove_image, launch_project, add_directories, create_share_link, delete_share_link and 15 more.
Does the Submitator MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Submitator MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_project and add_screenshot.
Has the Submitator MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.