Doorman MCP server
com.withdoorman/doormanwithdoorman.comstreamable-httpv0.1.0Scanned
Spam, pitch and fraud screening for website forms. Sign up, wire forms, test and review.
12 tools: 1 do something that can't be undone, 6 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 Doorman MCP server can do
The Doorman MCP server is published by withdoorman.com, a domain the MCP Registry verified. It has 12 tools. It can do things that cannot be undone, such as sending, paying or publishing (doorman_send_test_delivery) and create or change data (6 tools: doorman_signup, doorman_create_form, doorman_update_form, doorman_test_submission and 2 more), but cannot delete data. 5 tools only read.
1 tool reads private data (doorman_docs); 3 tools can send data out of your system (doorman_create_form, doorman_update_form and doorman_send_test_delivery).
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 14, 2026, version 0.1.0.
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.
12 tools
Can't be undone 1Claude Code: ask
doorman_send_test_deliverySend a sample delivery to the form's email/Slack/webhook destinations and report whether each one worked.Can send data outNo findings
Why it is in this group
- The name "doorman_send_test_delivery" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "doorman_send_test_delivery" says "send": it sends or publishes something to other people.
Description, as the server wrote it Send a sample delivery to the form's email/Slack/webhook destinations and report whether each one worked.
Changes things 6Claude Code: ask
doorman_contact_supportStuck, or something isn't working?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 Stuck, or something isn't working? Send the problem straight to Doorman's founder, with the error you hit. Your account context (plan, forms, recent errors, never keys) is attached, and the reply goes to the account email. Use it instead of guessing at a fix.
doorman_create_formCreate another form endpoint (one per distinct form on the site: contact, demo request, checkout, comments).Can send data outNo findings
Why it is in this group
- The name "doorman_create_form" says "create": a word for a change.
What it can reach
- outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Create another form endpoint (one per distinct form on the site: contact, demo request, checkout, comments).
doorman_label_submissionMark a submission real (delivers it if it was held or dropped) or spam.No findings
Why it is in this group
- The name "doorman_label_submission" says "label": a word for a change.
Description, as the server wrote it Mark a submission real (delivers it if it was held or dropped) or spam.
doorman_signupCreate a Doorman account for the user with a first form and an API key.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create a Doorman account for the user with a first form and an API key. Ask the user for their email first. They'll get an email to set a dashboard password. Creates the account's first form too and returns its id and action URL, plus the api_key (store it as DOORMAN_KEY in the project's local secrets file, never commit it). Only for new users: if they already have an account, ask for a key instead. Until the user clicks the confirmation link in that email, nothing is emailed to them (100 checks; Slack and webhooks work).
doorman_test_submissionJudge a sample message against a form's settings.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 Judge a sample message against a form's settings. Free, not forwarded, not counted. Use it to show the user Doorman working after setup (try one genuine enquiry and one sales pitch).
doorman_update_formChange a form's settings: context, destinations, thresholds, watch mode, allow/block lists.Can send data outNo findings
Why it is in this group
- The name "doorman_update_form" says "update": a word for a change.
What it can reach
- outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Change a form's settings: context, destinations, thresholds, watch mode, allow/block lists.
Only reads 5Show 5 read-only tools
doorman_docsRead how Doorman works and how to integrate it (the same text as /llms.txt).Reads private dataNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- private-dataThe name "doorman_docs" says "doc": it reads documents.
Description, as the server wrote it Read how Doorman works and how to integrate it (the same text as /llms.txt). Call this first if you haven't used Doorman before.
Annotations the server declares
- readOnlyHint: true
doorman_get_install_snippetGet ready-to-paste integration code for a form on a given platform.No findings
Why it is in this group
- The name "doorman_get_install_snippet" says "get": a word for reading.
Description, as the server wrote it Get ready-to-paste integration code for a form on a given platform. Use 'html' for static sites, 'react' for SPA client components, and 'fetch' (plain fetch with timeout and fallback: Workers, Node, Next, Deno), 'nextjs', 'express', 'python', 'ruby' or 'elixir' when the form already posts to the project's own backend.
Annotations the server declares
- readOnlyHint: true
doorman_list_formsList the account's forms with their action URLs and settings.No findings
Why it is in this group
- The name "doorman_list_forms" says "list": a word for reading.
Description, as the server wrote it List the account's forms with their action URLs and settings.
Annotations the server declares
- readOnlyHint: true
doorman_list_submissionsRecent submissions with their verdicts.No findings
Why it is in this group
- The name "doorman_list_submissions" says "list": a word for reading.
Description, as the server wrote it Recent submissions with their verdicts. Use review=true for held ones waiting for a human.
Annotations the server declares
- readOnlyHint: true
doorman_whoamiAccount, plan and this month's usage.No findings
Why it is in this group
- The name "doorman_whoami" says "whoami": a word for reading.
Description, as the server wrote it Account, plan and this month's usage.
Annotations the server declares
- readOnlyHint: true
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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.
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, 18:50 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
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (1 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://withdoorman.com/mcp: tools/list returned 12 tools to an anonymous client, including doorman_send_test_delivery (irreversible), doorman_signup (write), doorman_create_form (write), doorman_update_form (write), doorman_test_submission (write) and 2 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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http doorman https://withdoorman.com/mcpclaude mcp add --transport http doorman https://withdoorman.com/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__doorman__doorman_docs",
"mcp__doorman__doorman_whoami",
"mcp__doorman__doorman_list_forms",
"mcp__doorman__doorman_get_install_snippet",
"mcp__doorman__doorman_list_submissions"
],
"ask": [
"mcp__doorman__doorman_signup",
"mcp__doorman__doorman_create_form",
"mcp__doorman__doorman_update_form",
"mcp__doorman__doorman_test_submission",
"mcp__doorman__doorman_send_test_delivery",
"mcp__doorman__doorman_label_submission",
"mcp__doorman__doorman_contact_support"
],
"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 doorman. Review it before you use it.
Capability tags behind 4 rules
- mcp__doorman__doorman_docs private-data
- mcp__doorman__doorman_create_form outbound
- mcp__doorman__doorman_update_form outbound
- mcp__doorman__doorman_send_test_delivery outbound
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.withdoorman/doorman/verify?hash=72f5b097a62d7bdd30fe9d02c215b7eb2de27629fa5dbf1a385338763335112e" | jq -e '.changed == false'Pinned hash 72f5b097a62d, from Nov 14, 2026, 20:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.withdoorman/doorman/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.withdoorman/doorman)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
Doorman MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Doorman MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 7 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 Doorman MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Doorman MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: doorman_send_test_delivery.
What tools does the Doorman MCP server have?
- 12 tools: 1 irreversible, 6 write, 5 read. doorman_send_test_delivery, doorman_signup, doorman_create_form, doorman_update_form, doorman_test_submission, doorman_label_submission, doorman_contact_support, doorman_docs and 4 more.
Does the Doorman MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Doorman 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): doorman_create_form, doorman_update_form and doorman_send_test_delivery.
Has the Doorman MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.