Skip to content

Omniseal MCP server

io.github.PureCipher/omnisealPureCipherstreamable-httpv1.0.0Scanned

Conceal, retrieve, verify, and remove hidden files with PureCipher Omniseal.

4 tools: 1 can delete or cancel things, 2 change things and 1 only read.

Tools: 1 delete, 0 irreversible, 2 write, 1 read.
  • Reads private data · 1
  • Reads text others write · 4
  • Can send data out · 0
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Omniseal MCP server can do

The Omniseal MCP server is published by the GitHub account PureCipher. It has 4 tools. It can delete or cancel things (1 tool: remove_hidden_file) and create or change data (2 tools: seal_files and verify_sealed_file). 1 tool only reads.

1 tool reads private data (retrieve_secret_file); 4 tools bring in text other people can write (seal_files, retrieve_secret_file, verify_sealed_file and 1 more).

The fixed checks matched 4 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 16, 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 1Claude Code: deny
  • remove_hidden_fileReturn a new clean cover with the hidden payload removed; preserve the original sealed file.Reads text others write2 findings

    Why it is in this group

    • The name "remove_hidden_file" says "remove": a word for removing or ending something.
    • The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The input schema at properties.private_seed.description mentions "credential".

      Matched text

      inputSchema.properties.private_seed.description: "...d. Never use an account password or API credential."

      What this check looks for
    • Warn

      The server marks "remove_hidden_file" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "remove_hidden_file" says "remove": a word for removing or ending something.

      What this check looks for
    Description, as the server wrote it
    Return a new clean cover with the hidden payload removed; preserve the original sealed file. File results are binary MCP resources; this connector rejects results exceeding its 140,000-character limit. Inputs require actual file bytes or reachable URLs.

    Annotations the server declares

    • title: Remove hidden file
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Changes things 2Claude Code: ask
  • seal_filesConceal a secret file inside a cover file, returning a new sealed file without overwriting originals.Reads text others write1 finding

    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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The input schema at properties.private_seed.description mentions "credential".

      Matched text

      inputSchema.properties.private_seed.description: "...d. Never use an account password or API credential."

      What this check looks for
    Description, as the server wrote it
    Conceal a secret file inside a cover file, returning a new sealed file without overwriting originals. File results are binary MCP resources; this connector rejects results exceeding its 140,000-character limit. Inputs require actual file bytes or reachable URLs.

    Annotations the server declares

    • title: Seal files
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • verify_sealed_fileCheck whether an Omniseal sealed file shows signs of tampering.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    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
    Check whether an Omniseal sealed file shows signs of tampering. File results are binary MCP resources; this connector rejects results exceeding its 140,000-character limit. Inputs require actual file bytes or reachable URLs.

    Annotations the server declares

    • title: Verify sealed file
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • retrieve_secret_fileRecover the exact hidden file from an Omniseal sealed file using its private seed.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "retrieve_secret_file" says "retrieve": a word for reading.

    What it can reach

    • private-dataThe name "retrieve_secret_file" says "retrieve" and "secret": it reads secrets.
    • private-dataThe description's first sentence says "file": it reads files.
    • private-dataThe input names a file (input.sealed_file), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The input schema at properties.private_seed.description mentions "credential".

      Matched text

      inputSchema.properties.private_seed.description: "...d. Never use an account password or API credential."

      What this check looks for
    Description, as the server wrote it
    Recover the exact hidden file from an Omniseal sealed file using its private seed. File results are binary MCP resources; this connector rejects results exceeding its 140,000-character limit. Inputs require actual file bytes or reachable URLs.

    Annotations the server declares

    • title: Retrieve secret file
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • 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 outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
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.

Tools listed without sign-in

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 (1 destructive, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.purecipher.com/mcp?platform=claude: tools/list returned 4 tools to an anonymous client, including remove_hidden_file (destructive), seal_files (write), verify_sealed_file (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn3 info
  • The server marks "remove_hidden_file" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "remove_hidden_file" says "remove": a word for removing or ending something.

    What this check looks for
  • The input schema at properties.private_seed.description mentions "credential".

    Matched text

    inputSchema.properties.private_seed.description: "...d. Never use an account password or API credential."

    What this check looks for
  • The input schema at properties.private_seed.description mentions "credential".

    Matched text

    inputSchema.properties.private_seed.description: "...d. Never use an account password or API credential."

    What this check looks for
  • The input schema at properties.private_seed.description mentions "credential".

    Matched text

    inputSchema.properties.private_seed.description: "...d. Never use an account password or API credential."

    What this check looks for

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 omniseal https://api.purecipher.com/mcp?platform=claude
claude mcp add --transport http omniseal https://api.purecipher.com/mcp?platform=claude

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__omniseal__retrieve_secret_file"
    ],
    "ask": [
      "mcp__omniseal__seal_files",
      "mcp__omniseal__verify_sealed_file"
    ],
    "deny": [
      "mcp__omniseal__remove_hidden_file"
    ]
  }
}

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 omniseal. Review it before you use it.

Capability tags behind 4 rules
  • mcp__omniseal__seal_files untrusted-input
  • mcp__omniseal__retrieve_secret_file private-data, untrusted-input
  • mcp__omniseal__verify_sealed_file untrusted-input
  • mcp__omniseal__remove_hidden_file 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/io.github.PureCipher/omniseal/verify?hash=4efb76fd024d556e62f352d460d6e828d8a1faedc966ed5deda83528edbcb83f" | jq -e '.changed == false'

Pinned hash 4efb76fd024d, from Nov 16, 2026, 04:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.PureCipher/omniseal/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.PureCipher/omniseal
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.PureCipher/omniseal.svg)](https://radar.anlyon.com/servers/io.github.PureCipher/omniseal)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:18 UTC.

Omniseal MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Omniseal MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 4 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 Omniseal MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: remove_hidden_file.

Can the Omniseal 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 Omniseal MCP server have?

4 tools: 1 destructive, 2 write, 1 read. remove_hidden_file, seal_files, verify_sealed_file and retrieve_secret_file.

Does the Omniseal MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Omniseal MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Omniseal MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.