Approval Link — Quotes and Proofs MCP server
com.kurodalab/quote-proof-approvalkurodalab.comstreamable-httpv0.1.3Scanned
Quote/proof approval drafts. Free; creator account + OAuth: https://kurodalab.com/en/approval-link/
13 tools: 4 can delete or cancel things, 1 do something that can't be undone, 2 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 4
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
4 tools 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 Approval Link — Quotes and Proofs MCP server can do
The Approval Link — Quotes and Proofs MCP server is published by kurodalab.com, a domain the MCP Registry verified. It has 13 tools. It can delete or cancel things (4 tools: send_approval_request, advance_stage, cancel_approval and ask_person), do things that cannot be undone, such as sending, paying or publishing (create_approval_request) and create or change data (2 tools: export_receipt and add_revision). 6 tools only read.
1 tool reads private data (export_receipt); 4 tools bring in text other people can write (send_approval_request, advance_stage, cancel_approval and 1 more); 2 tools can send data out of your system (create_approval_request and send_approval_request). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way 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.
Last scanned Nov 15, 2026, version 0.1.3.
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.
13 tools
Deletes or cancels 4Claude Code: deny
advance_stageEmail the customer a work-progress update after approval.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 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 Email the customer a work-progress update after approval.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
ask_personEmail a named person a decision link and record their response.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 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 Email a named person a decision link and record their response. Provide one person or personId.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
cancel_approvalCancel a direct approval request and record why it was cancelled.Reads text others writeNo findings
Why it is in this group
- The name "cancel_approval" says "cancel": a word for removing or ending something.
- 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 Cancel a direct approval request and record why it was cancelled.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
send_approval_requestEmail a confirmed draft to its customer.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "send_approval_request" 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_approval_request" says "send": it sends or publishes something to other people.
Description, as the server wrote it Email a confirmed draft to its customer. Recheck the current recipient and version before sending.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
Can't be undone 1Claude Code: ask
create_approval_requestSave a customer quote or proof as a draft.Can send data outNo findings
Why it is in this group
- The name "create_approval_request" 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 Save a customer quote or proof as a draft. This does not send an email.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
Changes things 2Claude Code: ask
add_revisionSave a new unsent version after a customer requests changes.No findings
Why it is in this group
- The name "add_revision" says "add": a word for a change.
Description, as the server wrote it Save a new unsent version after a customer requests changes. The prior sent version stays intact.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
export_receiptReturn the PDF record for a completed customer approval as an embedded document.Reads private data1 finding
Why it is in this group
- The description's first verb is "return": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- private-dataThe description's first sentence says "return" and "document": it reads documents.
Findings
- Warn
The server marks "export_receipt" 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 description's first verb is "return": a word for reading.
Description, as the server wrote it Return the PDF record for a completed customer approval as an embedded document.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
Only reads 6Show 6 read-only tools
get_approvalRead one approval request, its current version, decisions, and delivery states.No findings
Why it is in this group
- The name "get_approval" says "get": a word for reading.
Description, as the server wrote it Read one approval request, its current version, decisions, and delivery states.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_decisionRead the latest answer or deadline status for one internal decision.No findings
Why it is in this group
- The name "get_decision" says "get": a word for reading.
Description, as the server wrote it Read the latest answer or deadline status for one internal decision.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_approvalsPage through this workspace’s approval requests and their recorded statuses.No findings
Why it is in this group
- The name "list_approvals" says "list": a word for reading.
Description, as the server wrote it Page through this workspace’s approval requests and their recorded statuses.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_internal_decisionsPage through this workspace’s internal ask_person decisions.No findings
Why it is in this group
- The name "list_internal_decisions" says "list": a word for reading.
Description, as the server wrote it Page through this workspace’s internal ask_person decisions. Filter by current status; notification state is separate from the answer.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_peopleList people who can answer a decision in this workspace.No findings
Why it is in this group
- The name "list_people" says "list": a word for reading.
Description, as the server wrote it List people who can answer a decision in this workspace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
wait_for_decisionWait up to 20 seconds for an internal answer or customer approval response.No findings
Why it is in this group
- The name "wait_for_decision" says "wait": a word for reading.
Description, as the server wrote it Wait up to 20 seconds for an internal answer or customer approval response. A pending timeout is not approval.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
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.
8 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- 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 out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__quote-proof-approval__export_receipt"
]
}
}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, 18:41 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
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://approval-link-account.kurodalab.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://approval-link-account.kurodalab.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (4 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://approval-link-account.kurodalab.com/mcp: tools/list returned 13 tools to an anonymous client, including send_approval_request (destructive), advance_stage (destructive), cancel_approval (destructive), ask_person (destructive), create_approval_request (irreversible) and 2 more
Findings
Matches of fixed checks, with the text they matched.
- Warnexport_receipt
The server marks "export_receipt" 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 description's first verb is "return": 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 0.1.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http quote-proof-approval https://approval-link-account.kurodalab.com/mcpclaude mcp add --transport http quote-proof-approval https://approval-link-account.kurodalab.com/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__quote-proof-approval__list_people",
"mcp__quote-proof-approval__list_internal_decisions",
"mcp__quote-proof-approval__get_decision",
"mcp__quote-proof-approval__get_approval",
"mcp__quote-proof-approval__wait_for_decision",
"mcp__quote-proof-approval__list_approvals"
],
"ask": [
"mcp__quote-proof-approval__export_receipt",
"mcp__quote-proof-approval__create_approval_request",
"mcp__quote-proof-approval__add_revision"
],
"deny": [
"mcp__quote-proof-approval__send_approval_request",
"mcp__quote-proof-approval__advance_stage",
"mcp__quote-proof-approval__cancel_approval",
"mcp__quote-proof-approval__ask_person"
]
}
}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 quote-proof-approval. Review it before you use it.
Capability tags behind 6 rules
- mcp__quote-proof-approval__export_receipt private-data
- mcp__quote-proof-approval__create_approval_request outbound
- mcp__quote-proof-approval__send_approval_request untrusted-input, outbound
- mcp__quote-proof-approval__advance_stage untrusted-input
- mcp__quote-proof-approval__cancel_approval untrusted-input
- mcp__quote-proof-approval__ask_person 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.kurodalab/quote-proof-approval/verify?hash=b8086d29f6d4af73a79411e0e0c9f0fecc95e699fd205dab85f55b4088aad201" | jq -e '.changed == false'Pinned hash b8086d29f6d4, from Nov 15, 2026, 10:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.kurodalab/quote-proof-approval/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.kurodalab/quote-proof-approval)Source: MCP Registry. Synced Nov 2, 2026, 06:17 UTC.
Approval Link — Quotes and Proofs MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Approval Link — Quotes and Proofs MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 7 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 Approval Link — Quotes and Proofs MCP server delete data?
- Yes. 4 tools can delete, cancel or revoke something: send_approval_request, advance_stage, cancel_approval and ask_person.
Can the Approval Link — Quotes and Proofs MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: create_approval_request.
What tools does the Approval Link — Quotes and Proofs MCP server have?
- 13 tools: 4 destructive, 1 irreversible, 2 write, 6 read. send_approval_request, advance_stage, cancel_approval, ask_person, create_approval_request, export_receipt, add_revision, list_people and 5 more.
Does the Approval Link — Quotes and Proofs MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Approval Link — Quotes and Proofs MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_approval_request and send_approval_request.
Has the Approval Link — Quotes and Proofs MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.