MCP servers › com.humanmailbox › mailbox
MCP server · registry snapshot 2026-10-30 · last tested 2026-10-30
mailbox MCP server
Registry name com.humanmailbox/mailbox
Human Mailbox — the publisher's title
by humanmailbox.com · domain (the registry's namespace rule)Website ↗
A physical postal address in Germany for AI agents. A human opens, scans and forwards your mail. — the publisher's description
Summary
com.humanmailbox/mailbox is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain humanmailbox.com. On 2026-10-30 ProtocolProbe connected to it in read-only mode and read its inventory: 32 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 32
- Last tested
- 2026-10-30
Tool list size
8,115 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (32 tools). Counted with Anthropic's token counter on 2026-10-30, from the tool list we read on 2026-10-30. Median across 25,738 counted servers: 2,858 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-10-30 (humanmailbox.com), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.0.0).
Observed fact
This server accepted a session without any credential and lists 2 tools whose name or declaration suggests they change data (update_account, send_message). That is our reading of the names; we did not call them. Source: our connection, 2026-10-30.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-30
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-10-29 (registry, as of the 2026-10-30 snapshot)
- First listed version
- 2026-10-29 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-10-30
- Package and repository
- checked 2026-10-30
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-10-29, listed on 2026-10-30 with version 1.0.0 (published 2026-10-29).
Source: the official MCP Registry list on 2026-10-29 and on 2026-10-30.
What it is
What does this server offer?
Observed inventoryNone of its 32 tools are described as changing anything. For 32 the reading was uncertain, so no mark is shown.
- register_mailbox
“Create your own mailbox at a physical street address in Germany.”
Publisher declares: open-world yes
12 inputs, 2 required
agent_namestringrequiredaddress_namestring“Name on your mail (2–60 chars), e.g.”operator_namestring“Responsible human or company.”operator_emailstringaccept_termsbooleanrequiredoperator_typestringoperator_countrystringpurposestring“What you will receive mail for.”agent_modelstringwebhook_urlstring“https URL that gets events (item.received, quote.ready ...).”open_policystring“standard = open + scan within 3 business days (included), same_day = on arrival day (+2 €), never = keep sealed.”found_viastring“Optional: where you found Human Mailbox (e.g.”
- start_demoon 1 other server
“Free demo mailbox, no registration: play money (€60 + letter credits), a scanned sample letter and a sealed sample parcel, a sample gift card code.”
3 inputs
agent_namestringagent_modelstringfound_viastring
- express_intereston 1 other server
“No account needed.”
6 inputs
kindstringnamestringemailstringcountry_wantedstringuse_casestringfound_viastring
- get_priceson 48 other servers
“Prices in EUR: mailbox 15 € per 30 days (3 letters included), letter 3 € (open + scan), parcel 9 €, bundles, same-day, forwarding, all 8 services (send letters, vouchers, purchases, digitizing, retur…”
Publisher declares: read-only yes · open-world no
Takes no inputs.
- get_accounton 123 other servers
“Your account, balance, address and counts.”
Publisher declares: read-only yes · open-world no
1 input
api_keystring“Your hm_...”
- get_addresson 8 other servers
“The street address to put on letters and parcels, with your mailbox code in the first line.”
Publisher declares: read-only yes · open-world no
2 inputs
stylestring“company (default) or person.”api_keystring“Your hm_...”
- buy_bundle
“Buy a bundle of letter credits (letters_1 3 €, letters_10 25 €, letters_100 200 €) or same-day credits (same_day_10, same_day_100).”
2 inputs, 1 required
bundlestringrequiredapi_keystring“Your hm_...”
- pay_item
“An item that arrived without credits or balance waits unopened (payment_status unpaid).”
2 inputs, 1 required
idstringrequiredapi_keystring“Your hm_...”
- announce_shipment
“Tell the human that something is on its way (tracking number helps).”
8 inputs
carrierstringtrackingstringsenderstringdescriptionstringexpected_atstringinstructionsstringopen_modestringapi_keystring“Your hm_...”
- list_shipmentson 3 other servers
“Your announced shipments.”
Publisher declares: read-only yes · open-world no
2 inputs
statusstringapi_keystring“Your hm_...”
- list_itemson 14 other servers
“Everything that arrived for you, newest first, with photo links.”
Publisher declares: read-only yes · open-world no
2 inputs
statusstringapi_keystring“Your hm_...”
- get_itemon 46 other servers
“Details of one arrived item; photos and scans are returned as images you can see.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
idstringrequiredapi_keystring“Your hm_...”
Show 20 more tools
- request_actionon 2 other servers
“Ask the human to do something with your mail, documents or parcels.”
Publisher declares: destructive no · open-world yes
23 inputs, 1 required
actionstringrequireditem_idstringshipment_idstring“Pre-book for an announced shipment that has not arrived yet.”notestringaddressobject“Destination for forward / courier.”senderobject“Optional return address printed on the forwarded item.”expressboolean“forward only: dispatch the same day (+5 €).”max_postage_eurnumber“forward/return: postage up to this amount is charged automatically.”same_dayboolean“scan only: open + scan today (+2 € or 1 same-day credit).”textstring“send_letter: the letter as plain text (printed as is).”pdf_base64string“send_letter: the letter as an A4 PDF, base64 (max 5 MB, b/w, up to 10 pages).”registeredstring“send_letter: registered mail (fee at cost).”label_pdf_base64string“ship_out: a prepaid shipping / return label as PDF, base64.”carrierstringreferencestring“ship_out: order or return number.”outputstring“digitize: what you want back.”productstring“buy_voucher: which gift card / voucher.”value_eurnumber“buy_voucher: face value (max 100).”shopstringwhatstring“buy_item: what to buy.”wherestring“buy_item: shop or place, if known.”max_price_eurnumber“buy_item: the most the item itself may cost (max 500).”api_keystring“Your hm_...”
- list_requestson 13 other servers
“Your orders and their status.”
Publisher declares: read-only yes · open-world no
2 inputs
statusstringapi_keystring“Your hm_...”
- get_requeston 16 other servers
“One order with result notes, tracking and files.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
idstringrequiredapi_keystring“Your hm_...”
- accept_quoteon 6 other servers
“Accept the quoted price of an order (status quote_ready) and pay it.”
2 inputs, 1 required
idstringrequiredapi_keystring“Your hm_...”
- cancel_requeston 7 other servers
“Cancel an order that has not started; paid money goes back to your balance.”
2 inputs, 1 required
idstringrequiredapi_keystring“Your hm_...”
- list_codeson 4 other servers
“Gift card / voucher codes that arrived by mail.”
Publisher declares: read-only yes · open-world no
1 input
api_keystring“Your hm_...”
- reveal_codes
“Reveal waiting codes (1 € per code, from balance or x402).”
2 inputs
idsarrayapi_keystring“Your hm_...”
- request_invoiceon 1 other server
“Only if you need an invoice: creates one (free, no VAT under § 19 UStG) for your payments that have none yet, or for the given payment_ids, and emails it (default: your operator email).”
4 inputs
payment_idsarraybillingobjectemailstringapi_keystring“Your hm_...”
- list_invoiceson 23 other servers
“Invoices you requested (with full text), plus payments that have no invoice yet.”
Publisher declares: read-only yes · open-world no
1 input
api_keystring“Your hm_...”
- contact_human
“Works without an account.”
10 inputs, 1 required
topicstringbodystringrequired“What you need or want to know.”subjectstringemailstring“Optional: where the answer should go.”namestringbudget_eurnumberdeadlinestringlocationstringmethod_wantedstring“topic payment_method: the method you want (e.g.”api_keystring“Your hm_...”
- check_inquiry
“Status and answers of an inquiry from contact_human.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
idstringrequiredticketstringapi_keystring“Your hm_...”
- get_balanceon 114 other servers
“Your balance and recent transactions.”
Publisher declares: read-only yes · open-world no
1 input
api_keystring“Your hm_...”
- get_summaryon 17 other servers
“This month: costs by kind, budget used, subscription, open orders, mail and shipments.”
Publisher declares: read-only yes · open-world no
1 input
api_keystring“Your hm_...”
- get_subscriptionon 11 other servers
“The mailbox costs 15 € per 30 days (3 letters opened and scanned included) and renews from your balance: status and paid_until.”
Publisher declares: read-only yes · open-world no
1 input
api_keystring“Your hm_...”
- pay_subscription
“Prepay 1–12 mailbox months (15 € each) from your balance or with x402.”
2 inputs
monthsintegerapi_keystring“Your hm_...”
- update_accounton 13 other servers
“Set budget_eur_month (spending limit for orders, null = none), webhook_url, open_policy (standard | same_day | never), address_name (name on your mail), auto_reveal_codes, or name your human operator…”
9 inputs
budget_eur_monthnumber or nullwebhook_urlstringopen_policystringaddress_namestringauto_reveal_codesbooleanoperator_namestringoperator_emailstringpurposestringapi_keystring“Your hm_...”
- top_upon 10 other servers
“Add money (EUR): method x402 (pay now in USDC at the current rate), btc (get a Bitcoin address + amount) or paypal (get a link for your human operator).”
4 inputs, 1 required
methodstringrequiredamount_eurnumberbundlestringapi_keystring“Your hm_...”
- check_top_up
“Re-check whether a Bitcoin or PayPal top-up was paid.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
idstringrequiredapi_keystring“Your hm_...”
- send_messageon 98 other servers
“Write to the human who handles your mail.”
5 inputs, 1 required
bodystringrequiredsubjectstringitem_idstringrequest_idstringapi_keystring“Your hm_...”
- list_messageson 44 other servers
“Messages between you and the human.”
Publisher declares: read-only yes · open-world no
1 input
api_keystring“Your hm_...”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-30.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 46% of 120
- Tools with a description
- 100% of 32
- Typical description length
- 173 characters
The tool set
Counted from the listing
- Tools
- 32
- Size of the list
- about 5,282 tokens for an agent to load (characters ÷ 4)
- Naming
- 32 of 32 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 32 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-30 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://humanmailbox.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mailbox": {
"url": "https://humanmailbox.com/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"mailbox": {
"type": "http",
"url": "https://humanmailbox.com/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"mailbox","type":"http","url":"https://humanmailbox.com/mcp"}'Claude Code
claude mcp add --transport http mailbox https://humanmailbox.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"mailbox": {
"type": "streamableHttp",
"url": "https://humanmailbox.com/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"mailbox": {
"httpUrl": "https://humanmailbox.com/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.mailbox] url = "https://humanmailbox.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"mailbox": {
"url": "https://humanmailbox.com/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://humanmailbox.com/mcp --transport http
- Optional settings the entry also lists (left out above): Authorization.
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint humanmailbox.com/mcp | Session opened | matches | our test · 2026-10-30 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-30 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-30. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about com.humanmailbox/mailbox
Answered from the data aboveWho publishes com.humanmailbox/mailbox?
The registry ties the namespace com.humanmailbox to the domain humanmailbox.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does com.humanmailbox/mailbox need an API key or sign-in?
It opened a session without any credential on 2026-10-30. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.humanmailbox/mailbox been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-30, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 298 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 32 tools, 0 resources, 0 prompts.
- 1,749 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “com.humanmailbox/mailbox: MCP server record.” Data checked 2026-10-30. https://protocolprobe.com/mcp/servers/com.humanmailbox/mailbox
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/com.humanmailbox/mailbox)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology