ncrypted MCP server
io.github.Seidl-Family/ncryptedSeidl-Familystreamable-httpv0.2.2Scanned
One-time, end-to-end encrypted secrets for agents. 0.005 USDC per secret via x402.
4 tools: 2 can delete or cancel things, 1 change things and 1 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 0
- 2 findings
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 ncrypted MCP server can do
The ncrypted MCP server is published by the GitHub account Seidl-Family. It has 4 tools. It can delete or cancel things (2 tools: ncrypted_read and ncrypted_burn) and create or change data (1 tool: ncrypted_create). 1 tool only reads.
2 tools read private data (ncrypted_read and ncrypted_status); 1 tool brings in text other people can write (ncrypted_read).
The fixed checks matched 2 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 0.2.2.
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
ncrypted_burnPermanently destroy an unread secret you created, so its link stops working (e.g.1 finding
Why it is in this group
- The description's first verb is "destroy": a word for removing or ending something.
- The description says "Permanently destroy".
- The server marks it destructive (destructiveHint: true).
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...recipient has the value, so rotate the credential. Only works for secrets you created (ne..."
Description, as the server wrote it Permanently destroy an unread secret you created, so its link stops working (e.g. it was sent to the wrong place or is no longer needed). Irreversible. Returns { burned: true } if it was destroyed, or { burned: false, status } if there was nothing left to destroy because it was already read, burned or expired; if it was already read, the recipient has the value, so rotate the credential. Only works for secrets you created (needs their receiptToken). Free.
Annotations the server declares
- destructiveHint: true
ncrypted_readOpen an ncrypted link (https://.../s/{id}#{key}) and return the secret.Reads private dataReads text others write1 finding
Why it is in this group
- The name "ncrypted_read" says "read": a word for reading.
- The description's first verb is "open": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- private-dataThe description's first sentence says "secret": it reads secrets.
- untrusted-inputThe description's first sentence says "open" and "http": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "ncrypted_read" destructive (destructiveHint: true), and its name says "read", a word for reading.
What this check looks forMatched text
annotations: {"destructiveHint":true,"idempotentHint":false}; The name "ncrypted_read" says "read": a word for reading.
Description, as the server wrote it Open an ncrypted link (https://.../s/{id}#{key}) and return the secret. This destroys it permanently. Free. Only use the value for the task at hand and do not repeat it in chat. To check whether someone opened a link you created, use ncrypted_status instead (it doesn't consume anything). Hosted mode: this server decrypts the secret for you, so it sees the plaintext briefly over TLS (never stored or logged). For end-to-end, zero-knowledge encryption run the local MCP server `npx -y @seidl-family/ncrypted-mcp` instead.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
Changes things 1Claude Code: ask
ncrypted_createStore a password, API key or sensitive note as a one-time link that self-destructs after a single read.No findings
Why it is in this group
- The name "ncrypted_create" says "create": a word for a change.
Description, as the server wrote it Store a password, API key or sensitive note as a one-time link that self-destructs after a single read. The first 3 per day are free (TTL up to 24h); after that each costs 0.005 USDC, paid via x402 on Base (your MCP client must support x402). Share the link with a person or another agent; never echo the secret in chat. Returns { link, id, receiptToken, expiresAt }; keep id and receiptToken to check delivery (ncrypted_status) or revoke the link (ncrypted_burn). Hosted mode: this server encrypts the secret for you, so it sees the plaintext briefly over TLS (never stored or logged). For end-to-end, zero-knowledge encryption run the local MCP server `npx -y @seidl-family/ncrypted-mcp` instead.
Only reads 1Show 1 read-only tool
ncrypted_statusCheck whether a secret you created has been opened yet, without consuming it.Reads private dataNo findings
Why it is in this group
- The name "ncrypted_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "secret": it reads secrets.
Description, as the server wrote it Check whether a secret you created has been opened yet, without consuming it. Returns { status, expiresAt, readAt? } where status is pending (not opened), read, burned or expired. Use it to confirm delivery, or before deciding to ncrypted_burn a link. Only works for secrets you created (needs their receiptToken); to open a link, use ncrypted_read. Free.
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 outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 19:00 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
- 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 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://ncrypted.ai/mcp: tools/list returned 4 tools to an anonymous client, including ncrypted_read (destructive), ncrypted_burn (destructive), ncrypted_create (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnncrypted_read
The server marks "ncrypted_read" destructive (destructiveHint: true), and its name says "read", a word for reading.
What this check looks forMatched text
annotations: {"destructiveHint":true,"idempotentHint":false}; The name "ncrypted_read" says "read": a word for reading.
- Infoncrypted_burn
The description mentions "credential".
What this check looks forMatched text
description: "...recipient has the value, so rotate the credential. Only works for secrets you created (ne..."
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 0.2.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http ncrypted https://ncrypted.ai/mcpclaude mcp add --transport http ncrypted https://ncrypted.ai/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__ncrypted__ncrypted_status"
],
"ask": [
"mcp__ncrypted__ncrypted_create"
],
"deny": [
"mcp__ncrypted__ncrypted_read",
"mcp__ncrypted__ncrypted_burn"
]
}
}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 ncrypted. Review it before you use it.
Capability tags behind 2 rules
- mcp__ncrypted__ncrypted_read private-data, untrusted-input
- mcp__ncrypted__ncrypted_status 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/io.github.Seidl-Family/ncrypted/verify?hash=6220b0242cda919fc4546eb0bfa13fc60179ccc1eda8d7a46031cbff6c7b794b" | jq -e '.changed == false'Pinned hash 6220b0242cda, from Nov 16, 2026, 04:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Seidl-Family/ncrypted/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Seidl-Family/ncrypted)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:21 UTC.
ncrypted MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ncrypted MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 2 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 ncrypted MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: ncrypted_read and ncrypted_burn.
Can the ncrypted 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 ncrypted MCP server have?
- 4 tools: 2 destructive, 1 write, 1 read. ncrypted_read, ncrypted_burn, ncrypted_create and ncrypted_status.
Does the ncrypted MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ncrypted MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ncrypted MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.