directory MCP server
com.submitmap/directorysubmitmap.comstreamable-httpv1.0.0Scanned
A directory of product launch platforms: where your product qualifies and how each form is filled.
11 tools: 6 change things and 5 only read.
- Reads private data · 2
- Reads text others write · 2
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
6 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.
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 directory MCP server can do
The directory MCP server is published by submitmap.com, a domain the MCP Registry verified. It has 11 tools. It can create or change data (6 tools: qualify_project, whoami, create_project, update_project and 2 more), but cannot delete data. 5 tools only read.
2 tools read private data (search_platforms and whoami); 2 tools bring in text other people can write (whoami and record_submission); 3 tools can send data out of your system (qualify_project, create_project and update_project). 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.
Last scanned Nov 11, 2026, version 1.0.0.
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.
11 tools
Changes things 6Claude Code: ask
create_projectStore a product on the account.Can 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
- 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 Store a product on the account. Before asking the maker anything, use what you can already see: a README, package metadata, the site's own copy and title, an assets or public folder. A maker working in their product's repository should be able to say 'add my product to SubmitMap' and get a filled-in project back, with questions only about what is genuinely not there. Fill in as much as you can, leave the rest, and come back with update_project. Facts drive what it qualifies for; the pack is what you will paste into forms later. Ask about images early: most platforms want a square logo and many want a cover, and every asset in the pack is two fields, the public address (logoUrl) and the file on the maker's machine (logoFile), because a form uploads the file and only the address can be shown back to them.
plan_submissionsWrite the run order for a project: which platforms, in what sequence, and why each one is where it is.No findings
Why it is in this group
- The description's first verb is "write": a word for a change.
Description, as the server wrote it Write the run order for a project: which platforms, in what sequence, and why each one is where it is. Anything already submitted to is dropped from the plan and named back to you in `alreadySubmitted`, because a plan is what is still ahead. Pass the platforms in the order they should be worked, with a short reason on each, plus a summary of the strategy. The plan appears on the maker's dashboard as a checklist that ticks itself off as submissions land. Anything already tracked is reordered rather than reset. Call it after qualify_project, using the `recommended` list it hands back, and if that response carried `questions`, put them to the maker before you plan: the order depends on the answers, and a plan written on an assumption is one they have to undo by hand. A plan costs nothing on any plan, so plan the whole run the product deserves rather than a short one sized to a guess about what the account can track.
qualify_projectGiven a product, work out which platforms it qualifies for right now, which it could qualify for after supplying something (with the exact list of what is missing), and which are s…Can send data outNo 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
- 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 Given a product, work out which platforms it qualifies for right now, which it could qualify for after supplying something (with the exact list of what is missing), and which are structurally out of reach. It also hands back `recommended`: the run in the order it should be worked, so the plan comes out of the directory rather than out of what you remember of the web. That order is decided by `goal` and `budget`, and when they have not been answered the response says what it assumed and carries the questions to put to the maker: ask them, call again with the answers, and store them with update_project so nobody asks twice. Needs no account: describe the product inline. Every field is optional and an unanswered field becomes a gap to fill rather than a rejection.
submission_playbookEverything needed to submit a stored project to one platform, yourself, in the maker's browser: a preflight of what is still missing, the sign-in plan (on the first submission it c…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.
Description, as the server wrote it Everything needed to submit a stored project to one platform, yourself, in the maker's browser: a preflight of what is still missing, the sign-in plan (on the first submission it carries a question for the maker: hand every login back to them, or use the Google address they write out, which you then pass back as signInAs), the pack values mapped onto the fields the form asks for, the steps, the gotchas, the agentGotchas (traps in the form itself), and the call to make afterwards. Read the preflight before opening a tab. One brief is out at a time per project: ask for the next platform only after record_submission has answered this one, because until then this tool refuses the next brief and names the one still open. Do not fetch briefs ahead or in parallel. This is the tool the free plan meters: it covers the same submissions the dashboard tracks, plus any platform the account has already sent to, and past that it says so and points at the upgrade rather than answering.
update_projectFill in or correct a stored project.Can send data outNo findings
Why it is in this group
- The name "update_project" says "update": a word for a change.
What it can reach
- 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 Fill in or correct a stored project. Facts and pack are merged into what is there, so you can add one field at a time as the maker answers.
whoamiWhich SubmitMap account this token belongs to, named by its email address, which plan it is on, and what it already holds.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
- The description's first verb is "submit": a word for a change.
What it can reach
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe description's first sentence says "submit" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Which SubmitMap account this token belongs to, named by its email address, which plan it is on, and what it already holds. Call it first if you are unsure whether the maker is connected, and tell them the address it reports: it is the only way either of you can tell one of their accounts from another. It does not hand you the plan's limits and you do not need them to work: plan the whole run, and a limit says so at the write it stops.
Only reads 5Show 5 read-only tools
get_platformFull record for one platform: eligibility, disqualifiers, step-by-step submission instructions, requirements, gotchas and expected outcome.No findings
Why it is in this group
- The name "get_platform" says "get": a word for reading.
Description, as the server wrote it Full record for one platform: eligibility, disqualifiers, step-by-step submission instructions, requirements, gotchas and expected outcome. All of that is free, and it is what decides whether this product should be submitted here at all. Pass brief: true to also get agentPrompt, the brief for that platform's form, and agentGotchas, the traps that only bite something filling it (a placeholder that contradicts its label, a second email input belonging to a newsletter, a honeypot). The brief spends one of the account's tracked platforms, so ask for it once the maker has decided to fill this form, not while you are still choosing between platforms. For a stored project, submission_playbook returns the same brief with the maker's values already in it.
list_projectsThe projects on this account, each with its facts (eligibility answers) and its pack (what a submission form asks for), plus what is still missing from the pack.No findings
Why it is in this group
- The name "list_projects" says "list": a word for reading.
Description, as the server wrote it The projects on this account, each with its facts (eligibility answers) and its pack (what a submission form asks for), plus what is still missing from the pack. Call it whenever the maker says "my product" or "my project" without naming one: it is how you find out which project they mean, and every other account tool takes the id it returns.
list_submissionsWhere every submission for a project stands: what went out, when, what came back, and what is still waiting.No findings
Why it is in this group
- The name "list_submissions" says "list": a word for reading.
Description, as the server wrote it Where every submission for a project stands: what went out, when, what came back, and what is still waiting. This is the tool behind "check my submissions", "what did I submit", "did I ever submit to that one" and "how is my launch going", so answer those from here instead of asking the maker to remember. Start with list_projects if they have not named a project.
record_submissionLog what happened to the dashboard: the listing URL, when it was sent, when it goes live.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "log": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "log" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Log what happened to the dashboard: the listing URL, when it was sent, when it goes live. Call it as soon as a submission lands, before you ask for the next brief, including when it is only queued for review, and including when you are not sure it landed: that is what `attempted` is for. The next brief on this project is refused until this call is made. A platform that needs the maker (a captcha, a login, a payment, a file, an address to confirm) is recorded as `planned` with a note saying what you need from them: that hands it back without claiming an outcome, and frees the run to carry on. If the live platform did not match what the brief said, put the difference in `differsFromRecord`. This costs nothing on any plan and no status costs more than another, so record what actually happened: the brief was what spent the tracked platform, and leaving the row wrong now only makes the run harder to follow.
search_platformsSearch the SubmitMap directory of startup launch platforms and directories.Reads private dataNo findings
Why it is in this group
- The name "search_platforms" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "directory": it reads files.
Description, as the server wrote it Search the SubmitMap directory of startup launch platforms and directories. Filter by free-text query, category, pricing, link type, backlink requirement, approval speed or domain rating, and with a token leave out the ones this project has already been sent to. This is the tool behind "find me a small directory I can submit to right now": it is the whole directory, so answer from it rather than from what you remember of the web. Returns summaries; call get_platform for the full record including the submission steps.
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.
12 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 untrusted-input tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__directory__record_submission",
"mcp__directory__whoami"
]
}
}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 20, 2026, 18:48 UTC, unchanged since Oct 22, 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
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://submitmap.com/.well-known/oauth-protected-resource
- Authorization servers
- https://submitmap.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://submitmap.com/api/mcp: tools/list returned 11 tools to an anonymous client, including qualify_project (write), whoami (write), create_project (write), update_project (write), submission_playbook (write) and 1 more
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http directory https://submitmap.com/api/mcpclaude mcp add --transport http directory https://submitmap.com/api/mcpRun 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__directory__search_platforms",
"mcp__directory__get_platform",
"mcp__directory__list_projects",
"mcp__directory__record_submission",
"mcp__directory__list_submissions"
],
"ask": [
"mcp__directory__qualify_project",
"mcp__directory__whoami",
"mcp__directory__create_project",
"mcp__directory__update_project",
"mcp__directory__submission_playbook",
"mcp__directory__plan_submissions"
],
"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 directory. Review it before you use it.
Capability tags behind 6 rules
- mcp__directory__search_platforms private-data
- mcp__directory__qualify_project outbound
- mcp__directory__whoami private-data, untrusted-input
- mcp__directory__create_project outbound
- mcp__directory__update_project outbound
- mcp__directory__record_submission untrusted-input
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.submitmap/directory/verify?hash=6864371693d193f5fab50fcb36d85e1e4f57c46ae350edb74fdadbecf6af58d4" | jq -e '.changed == false'Pinned hash 6864371693d1, from Nov 11, 2026, 02:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.submitmap/directory/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.submitmap/directory)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:05 UTC.
directory MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the directory MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 6 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 directory MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the directory 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 directory MCP server have?
- 11 tools: 6 write, 5 read. qualify_project, whoami, create_project, update_project, submission_playbook, plan_submissions, search_platforms, get_platform and 3 more.
Does the directory MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the directory MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): qualify_project, create_project and update_project.
Has the directory MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.