OnceAsk MCP server
io.github.rsb6061/onceaskrsb6061streamable-httpv1.0.0Scanned
MCP server for OnceAsk, the AI-native current-address layer for people and agents.
4 tools: 2 can delete or cancel things, 1 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 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 OnceAsk MCP server can do
The OnceAsk MCP server is published by the GitHub account rsb6061. It has 4 tools. It can delete or cancel things (2 tools: request_delivery_permission and send_handwritten_card) and create or change data (1 tool: resolve_delivery). 1 tool only reads.
3 tools bring in text other people can write (request_delivery_permission, list_handwritten_cards and send_handwritten_card); 1 tool can send data out of your system (send_handwritten_card).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 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.
4 tools
Deletes or cancels 2Claude Code: deny
request_delivery_permissionAfter the user explicitly confirms they want the recipient contacted, ask OnceAsk to request a current delivery address/permission.Reads text others writeNo findings
Why it is in this group
- The name "request_delivery_permission" says "request": 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 After the user explicitly confirms they want the recipient contacted, ask OnceAsk to request a current delivery address/permission. Accepts either a recipientId from resolve_delivery or a person's name/email. OnceAsk searches its contacts and connected Google/Gmail-derived people, then emails the secure request when possible without revealing the recipient email or street address to the agent.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
send_handwritten_cardFulfill a handwritten card using a delivery token returned by resolve_delivery.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "send_handwritten_card" says "send": a word for sending, and what is sent cannot be taken back.
- 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.
- outboundThe name "send_handwritten_card" says "send": it sends or publishes something to other people.
Description, as the server wrote it Fulfill a handwritten card using a delivery token returned by resolve_delivery. OnceAsk sends the recipient address directly to the fulfillment provider; the agent does not receive it.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
Changes things 1Claude Code: ask
resolve_deliveryPreferred privacy-preserving way to send something to a person.1 finding
Why it is in this group
- The name "resolve_delivery" says "resolve": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "resolve_delivery" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "resolve_delivery" says "resolve": a word for reading.
Description, as the server wrote it Preferred privacy-preserving way to send something to a person. Searches OnceAsk first and, when connected, can discover a missing person from Google Contacts or Gmail interactions. Resolves to a short-lived one-time delivery token when recipient permission and a current address exist. Does not return the street address.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
Only reads 1Show 1 read-only tool
list_handwritten_cardsList available Handwrytten card designs and handwriting styles for privacy-preserving fulfillment.Reads text others writeNo findings
Why it is in this group
- The name "list_handwritten_cards" says "list": a word for reading.
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 List available Handwrytten card designs and handwriting styles for privacy-preserving fulfillment. Does not expose recipient address data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: 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 private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- 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, 19:10 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
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://onceask.com/.well-known/oauth-protected-resource
- Authorization servers
- https://onceask.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (2 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://onceask.com/_api/mcp: tools/list returned 4 tools to an anonymous client, including request_delivery_permission (destructive), send_handwritten_card (destructive), resolve_delivery (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnresolve_delivery
The server marks "resolve_delivery" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "resolve_delivery" says "resolve": a word for reading.
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 onceask https://onceask.com/_api/mcpclaude mcp add --transport http onceask https://onceask.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__onceask__list_handwritten_cards"
],
"ask": [
"mcp__onceask__resolve_delivery"
],
"deny": [
"mcp__onceask__request_delivery_permission",
"mcp__onceask__send_handwritten_card"
]
}
}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 onceask. Review it before you use it.
Capability tags behind 3 rules
- mcp__onceask__request_delivery_permission untrusted-input
- mcp__onceask__list_handwritten_cards untrusted-input
- mcp__onceask__send_handwritten_card untrusted-input, 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/io.github.rsb6061/onceask/verify?hash=e1abc9b6d1d01d7a4262189f4d678d34c97701fb5545b9696cb3983e81f7fe50" | jq -e '.changed == false'Pinned hash e1abc9b6d1d0, from Nov 20, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.rsb6061/onceask/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.rsb6061/onceask)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:46 UTC.
OnceAsk MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the OnceAsk MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the OnceAsk MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: request_delivery_permission and send_handwritten_card.
Can the OnceAsk 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 OnceAsk MCP server have?
- 4 tools: 2 destructive, 1 write, 1 read. request_delivery_permission, send_handwritten_card, resolve_delivery and list_handwritten_cards.
Does the OnceAsk MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the OnceAsk MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_handwritten_card.
Has the OnceAsk MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.