Skip to content

Mosaya MCP server

ai.mosaya/practicemosaya.aistreamable-httpv0.1.0Scanned

Guided practices inside your conversation: meditation, breathwork, mindfulness and more.

5 tools: 1 change things and 4 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes 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 Mosaya MCP server can do

The Mosaya MCP server is published by mosaya.ai, a domain the MCP Registry verified. It has 5 tools. It can create or change data (1 tool: start_practice), but cannot delete data. 4 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

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, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 17, 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.

5 tools

Changes things 1Claude Code: ask
  • start_practiceOpen one Mosaya practice, ready to begin: the person picks a length, taps Begin, and the sit runs full screen with a bell at the start and the end, then a short celebration.1 finding

    Why it is in this group

    • The name "start_practice" says "start": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "start_practice" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "start_practice" says "start": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Open one Mosaya practice, ready to begin: the person picks a length, taps Begin, and the sit runs full screen with a bell at the start and the end, then a short celebration. Use after find_practice, or when they name a practice. Nothing is stored.

    Annotations the server declares

    • title: Start a practice
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
Only reads 4Show 4 read-only tools
  • find_practiceOffer the person up to three Mosaya practices they can do right here (meditation, breathwork, mindfulness, loving-kindness, gratitude, a focus timer and more).No findings

    Why it is in this group

    • The name "find_practice" says "find": a word for reading.
    Description, as the server wrote it
    Offer the person up to three Mosaya practices they can do right here (meditation, breathwork, mindfulness, loving-kindness, gratitude, a focus timer and more). Use when they want to meditate, calm down, settle a racing mind, sleep, focus, or ask for a practice by name. Shows a card; nothing is stored. If their words sound like crisis, the card shows care and crisis lines instead of practices.

    Annotations the server declares

    • title: Find a practice
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • get_pieceRead one piece from the Wisdom library at mosaya.ai by its slug: its title, summary, opening answer, topic, byline and link.No findings

    Why it is in this group

    • The name "get_piece" says "get": a word for reading.
    Description, as the server wrote it
    Read one piece from the Wisdom library at mosaya.ai by its slug: its title, summary, opening answer, topic, byline and link. The whole piece is at the link. Not medical, therapy or crisis help.

    Annotations the server declares

    • title: Read a Wisdom library piece
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • list_topicsThe thirteen topics of the Wisdom library at mosaya.ai, each with its short answer and link.No findings

    Why it is in this group

    • The name "list_topics" says "list": a word for reading.
    Description, as the server wrote it
    The thirteen topics of the Wisdom library at mosaya.ai, each with its short answer and link.

    Annotations the server declares

    • title: List the Wisdom library's topics
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • search_wisdomSearch the Wisdom library at mosaya.ai: short essays on inner life, burnout, grief, relationships, meditation, work and the Way of MOS, by Mos, your sage, and Bodhi Sacha.No findings

    Why it is in this group

    • The name "search_wisdom" says "search": a word for reading.
    Description, as the server wrote it
    Search the Wisdom library at mosaya.ai: short essays on inner life, burnout, grief, relationships, meditation, work and the Way of MOS, by Mos, your sage, and Bodhi Sacha. Returns up to five pieces, each with its short answer and link. Not medical, therapy or crisis help. If the words sound like crisis, it answers with care and crisis lines by country, written in its text, instead of pieces.

    Annotations the server declares

    • title: Search the Wisdom library
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: 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 or untrusted-input or outbound.

Reads private data0
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 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 19, 2026, 17:22 UTC, unchanged since Nov 5, 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
1
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.mosaya.ai/api/mcp: tools/list returned 5 tools to an anonymous client, including start_practice (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "start_practice" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "start_practice" says "start": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 added.+3 addedView diff

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http practice https://www.mosaya.ai/api/mcp
claude mcp add --transport http practice https://www.mosaya.ai/api/mcp

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__practice__find_practice",
      "mcp__practice__search_wisdom",
      "mcp__practice__get_piece",
      "mcp__practice__list_topics"
    ],
    "ask": [
      "mcp__practice__start_practice"
    ],
    "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 practice. Review it before you use it.

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/ai.mosaya/practice/verify?hash=2eaca4875282359993b7826786cbfeaed05810b2303e1fb2801ba289b15b32f6" | jq -e '.changed == false'

Pinned hash 2eaca4875282, from Nov 17, 2026, 22:17 UTC.

Watch

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

https://radar.anlyon.com/servers/ai.mosaya/practice/changes.xml

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

Badge

Anlyon Radar badge for ai.mosaya/practice
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.mosaya/practice.svg)](https://radar.anlyon.com/servers/ai.mosaya/practice)

Source: MCP Registry. Synced Nov 4, 2026, 07:17 UTC.

Mosaya MCP server: questions and answers

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

Is the Mosaya MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 1 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 Mosaya MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Mosaya 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 Mosaya MCP server have?

5 tools: 1 write, 4 read. start_practice, find_practice, search_wisdom, get_piece and list_topics.

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

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

Does the Mosaya MCP server send data to outside services?

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

Has the Mosaya MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.