token-of-esteem MCP server
com.tokenofesteem/token-of-esteemtokenofesteem.comstreamable-httpv0.1.0Scanned
A press your agent can commission: a funny, personalized printed booklet, mailed as a gift.
12 tools: 1 can delete or cancel things, 1 do something that can't be undone, 2 change things and 8 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 1 does something that can't be undone. 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 token-of-esteem MCP server can do
The token-of-esteem MCP server is published by tokenofesteem.com, a domain the MCP Registry verified. It has 12 tools. It can delete or cancel things (1 tool: cancel_gift), do things that cannot be undone, such as sending, paying or publishing (create_gift) and create or change data (2 tools: validate_brief and create_setup_link). 8 tools only read.
1 tool reads private data (get_pricing); 1 tool brings in text other people can write (get_gift); 1 tool can send data out of your system (create_gift). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 14, 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.
12 tools
Deletes or cancels 1Claude Code: deny
cancel_giftCancel an in-flight gift and receive the refund amount.No findings
Why it is in this group
- The name "cancel_gift" says "cancel": a word for removing or ending something.
Description, as the server wrote it Cancel an in-flight gift and receive the refund amount. Free. Only possible before the booklet goes to print; once printing has started it fails with cancel_too_late. Pass the gift_id from create_gift and an optional reason for your records.
Can't be undone 1Claude Code: ask
create_giftPlace the order: write, print, and mail the booklet.Can send data outNo findings
Why it is in this group
- The name "create_gift" says "create": a word for a change.
- The input addresses people (input.recipient): what it sends cannot be taken back.
What it can reach
- outboundThe input takes a destination (input.recipient): what the tool writes goes there.
Description, as the server wrote it Place the order: write, print, and mail the booklet. CHARGES the buyer. The recipient is whoever you name in recipient, which may be your own user. Idempotent on idempotency_key for 24 hours. Pass shared_payment_token to pay tokenlessly, or omit it to charge the account's saved card.
Changes things 2Claude Code: ask
create_setup_linkReturn a hosted Stripe link for the buyer to save a card or wallet to the account.No findings
Why it is in this group
- The name "create_setup_link" says "create": a word for a change.
Description, as the server wrote it Return a hosted Stripe link for the buyer to save a card or wallet to the account. After that, create_gift without a shared_payment_token charges the saved card.
validate_briefRun the content policy on a brief without charging or ordering.No findings
Why it is in this group
- The name "validate_brief" says "validate": a word for reading.
- The description's first verb is "run": a word for a change.
Description, as the server wrote it Run the content policy on a brief without charging or ordering. Free. Call before create_gift so a refusal surfaces early. A booklet that would wound the recipient is refused here, not at charge time.
Only reads 8Show 8 read-only tools
get_accountReturn this account's spending caps and month-to-date spend.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it Return this account's spending caps and month-to-date spend. Free. Use it to confirm budget before create_gift.
get_giftFetch a gift by gift_id and return its full resource: status, voice, format, pricing, the recipient, and fulfillment (Lulu job id, carrier, tracking URL, estimated delivery).Reads text others writeNo findings
Why it is in this group
- The name "get_gift" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch a gift by gift_id and return its full resource: status, voice, format, pricing, the recipient, and fulfillment (Lulu job id, carrier, tracking URL, estimated delivery). Free and read-only. Use it to poll progress after create_gift: status advances through the pipeline to shipped then delivered, or ends at held, refused, cancelled, or failed.
get_pricingCompute the exact total for a hypothetical gift (format, voice, image model, ship_to) before you commit.Reads private dataNo findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "commit": it reads repositories.
Description, as the server wrote it Compute the exact total for a hypothetical gift (format, voice, image model, ship_to) before you commit. Free, no order is created. Call before create_gift so you know the charge.
list_formatsList supported booklet formats.No findings
Why it is in this group
- The name "list_formats" says "list": a word for reading.
Description, as the server wrote it List supported booklet formats. There is one today: manual_v1, a 16-page booklet. Free, no side effects.
list_giftsPaginated list of gifts on the account, with optional status and date filters.No findings
Why it is in this group
- The name "list_gifts" says "list": a word for reading.
Description, as the server wrote it Paginated list of gifts on the account, with optional status and date filters. Free.
list_image_modelsList supported cover image models and their per-call cost.No findings
Why it is in this group
- The name "list_image_models" says "list": a word for reading.
Description, as the server wrote it List supported cover image models and their per-call cost. Free, no side effects.
list_recipientsReturn the account's saved recipients (address book).No findings
Why it is in this group
- The name "list_recipients" says "list": a word for reading.
Description, as the server wrote it Return the account's saved recipients (address book). Free. Reuse a recipient_id in create_gift instead of re-entering an address.
list_voicesList the three comedic voices (Hype Man, Best Friend Roast, Conspiracy Theorist) and the cover image model each prefers.No findings
Why it is in this group
- The name "list_voices" says "list": a word for reading.
Description, as the server wrote it List the three comedic voices (Hype Man, Best Friend Roast, Conspiracy Theorist) and the cover image model each prefers. Free, no side effects. Call this first to pick a voice.
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.
1 path in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__token-of-esteem__create_gift"
]
}
}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, 18:48 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
- 4
- 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 4 tools that change things (1 destructive, 1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.tokenofesteem.com/v1/mcp: tools/list returned 12 tools to an anonymous client, including cancel_gift (destructive), create_gift (irreversible), validate_brief (write), create_setup_link (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http token-of-esteem https://mcp.tokenofesteem.com/v1/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http token-of-esteem https://mcp.tokenofesteem.com/v1/mcp --header 'Authorization: <your-authorization>'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.
{
"permissions": {
"allow": [
"mcp__token-of-esteem__list_voices",
"mcp__token-of-esteem__list_formats",
"mcp__token-of-esteem__list_image_models",
"mcp__token-of-esteem__get_pricing",
"mcp__token-of-esteem__get_gift",
"mcp__token-of-esteem__list_gifts",
"mcp__token-of-esteem__get_account",
"mcp__token-of-esteem__list_recipients"
],
"ask": [
"mcp__token-of-esteem__validate_brief",
"mcp__token-of-esteem__create_gift",
"mcp__token-of-esteem__create_setup_link"
],
"deny": [
"mcp__token-of-esteem__cancel_gift"
]
}
}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 token-of-esteem. Review it before you use it.
Capability tags behind 3 rules
- mcp__token-of-esteem__get_pricing private-data
- mcp__token-of-esteem__create_gift outbound
- mcp__token-of-esteem__get_gift 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/com.tokenofesteem/token-of-esteem/verify?hash=9b02e20724cbe1c62aa517fbae7e75ecba8911718524dacb24cd23c6dd186413" | jq -e '.changed == false'Pinned hash 9b02e20724cb, from Nov 14, 2026, 15:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.tokenofesteem/token-of-esteem/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.tokenofesteem/token-of-esteem)Source: MCP Registry. Synced Oct 21, 2026, 18:07 UTC.
token-of-esteem MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the token-of-esteem MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 4 of which can change, send or delete something, and 0 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 token-of-esteem MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: cancel_gift.
Can the token-of-esteem MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: create_gift.
What tools does the token-of-esteem MCP server have?
- 12 tools: 1 destructive, 1 irreversible, 2 write, 8 read. cancel_gift, create_gift, validate_brief, create_setup_link, list_voices, list_formats, list_image_models, get_pricing and 4 more.
Does the token-of-esteem MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the token-of-esteem 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): create_gift.
Has the token-of-esteem MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.