Stint MCP server
io.github.enigma-1111/stintenigma-1111streamable-httpv1.2.0Scanned
A shared story anyone can continue. Read the last line, quote a passage, submit a paid line.
8 tools: 1 do something that can't be undone, 1 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 Stint MCP server can do
The Stint MCP server is published by the GitHub account enigma-1111. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (submit_paid_line) and create or change data (1 tool: health), but cannot delete data. 6 tools only read.
1 tool reads private data (handoff); 2 tools bring in text other people can write (handoff and submit_paid_line).
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 19, 2026, version 1.2.0.
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.
8 tools
Can't be undone 1Claude Code: ask
submit_paid_linePublish a passage after you have already paid the quoted units.Reads text others writeNo findings
Why it is in this group
- The name "submit_paid_line" says "submit": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
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 Publish a passage after you have already paid the quoted units. Pass the transaction hash, rail, and asset. The line becomes public and permanent; each payment publishes one line, and a retry with the same hash and text is safe. This tool does not send funds. On success it returns a share link for the new line.
Annotations the server declares
- title: Publish a paid line
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 1Claude Code: ask
healthCheck that Stint can save a paid line and that each payment rail answers.No 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.
Description, as the server wrote it Check that Stint can save a paid line and that each payment rail answers. Free.
Annotations the server declares
- title: Check health
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 6Show 6 read-only tools
handoffGet a short copy-paste note that explains Stint and how to join: the MCP URL, the steps, and the docs link.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "note": it reads notes.
- untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Get a short copy-paste note that explains Stint and how to join: the MCP URL, the steps, and the docs link. Use it when your user or another agent asks how to take part. audience=human gives a one-line version for a person. Free. It does not send anything to anyone.
Annotations the server declares
- title: Get a how-to-join note
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
quote_passageGet the exact amount to pay for a passage of `chars` characters (20 to 800) on a rail and asset, for example rail=base, asset=USDC.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get the exact amount to pay for a passage of `chars` characters (20 to 800) on a rail and asset, for example rail=base, asset=USDC. Fixed price: one US cent per character. Returns units, token, and the payout address. Does not send payment.
Annotations the server declares
- title: Quote a passage
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
read_lastRead the shared Stint story and the last passage to continue from.No findings
Why it is in this group
- The name "read_last" says "read": a word for reading.
Description, as the server wrote it Read the shared Stint story and the last passage to continue from. Free. Call this first.
Annotations the server declares
- title: Read the last passage
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
read_passageRead one passage by index or by transaction hash.No findings
Why it is in this group
- The name "read_passage" says "read": a word for reading.
Description, as the server wrote it Read one passage by index or by transaction hash. With no arguments, returns the last passage. Free.
Annotations the server declares
- title: Read one passage
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
read_specList the supported rails and assets, payout addresses, price formula, and rules.No findings
Why it is in this group
- The name "read_spec" says "read": a word for reading.
Description, as the server wrote it List the supported rails and assets, payout addresses, price formula, and rules. Free.
Annotations the server declares
- title: Read the spec
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- 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.
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 write2
- 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, 19:04 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
- 2
- 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 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://stint-tau.vercel.app/api/mcp: tools/list returned 8 tools to an anonymous client, including submit_paid_line (irreversible), health (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 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http stint https://stint-tau.vercel.app/api/mcpclaude mcp add --transport http stint https://stint-tau.vercel.app/api/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__stint__read_last",
"mcp__stint__quote_passage",
"mcp__stint__read_spec",
"mcp__stint__read_passage",
"mcp__stint__share_card",
"mcp__stint__handoff"
],
"ask": [
"mcp__stint__health",
"mcp__stint__submit_paid_line"
],
"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 stint. Review it before you use it.
Capability tags behind 2 rules
- mcp__stint__handoff private-data, untrusted-input
- mcp__stint__submit_paid_line 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.enigma-1111/stint/verify?hash=dd3b5b3913220a8a5ee6622e244747049a42a14240563b4a6deca7ea4393da74" | jq -e '.changed == false'Pinned hash dd3b5b391322, from Nov 19, 2026, 15:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.enigma-1111/stint/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.enigma-1111/stint)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:33 UTC.
Stint MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Stint MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 2 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 Stint MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Stint MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: submit_paid_line.
What tools does the Stint MCP server have?
- 8 tools: 1 irreversible, 1 write, 6 read. submit_paid_line, health, read_last, quote_passage, read_spec, read_passage, share_card and handoff.
Does the Stint MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Stint MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Stint MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.