Sternly MCP server
ai.sternly/verifysternly.aistreamable-httpv0.1.0Scanned
Checks finished AI work after it is done: figures, citations and quotations, with a signed record.
4 tools: 1 do something that can't be undone, 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 2
- No findings
Sign-in required, OAuth metadata published. 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 Sternly MCP server can do
The Sternly MCP server is published by sternly.ai, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (propose_definitions) and create or change data (1 tool: submit_claim_bundle), but cannot delete data. 2 tools only read.
1 tool brings in text other people can write (submit_claim_bundle); 2 tools can send data out of your system (submit_claim_bundle and propose_definitions).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint asks for sign-in and publishes OAuth metadata.
Last scanned Nov 8, 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.
4 tools
Can't be undone 1Claude Code: ask
propose_definitionsSend a definition the person wants to add, in their words, to the workspace, where a person approves it before it is used.Can send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send a definition the person wants to add, in their words, to the workspace, where a person approves it before it is used. Nothing proposed here takes effect by itself.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 1Claude Code: ask
submit_claim_bundleHand finished work to Sternly for an independent check after the fact.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "submit_claim_bundle" says "submit": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.capture.channel): what the tool writes goes there.
Description, as the server wrote it Hand finished work to Sternly for an independent check after the fact. Send the final text exactly as the person received it, what the person asked for in their own words, and the files, sources and programs you already used, with what each program printed. Send the work as it is: do not rewrite, shorten or add to it for Sternly, and do not mark which part came from where; Sternly reads the work itself. When the work is someone else's (the other side's brief, a filing before the court), say so in policy.mode, and name a producer only if you know who made it. Returns a check id and a link to give the person; get_check returns the result. With wait set to false, Sternly answers at once with the status running, and the check goes on.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
get_checkThe status of a check Sternly runs (running, done or failed) and, once it is done, its result: its headline, counts, depth, findings and the link to its signed evidence package.No findings
Why it is in this group
- The name "get_check" says "get": a word for reading.
Description, as the server wrote it The status of a check Sternly runs (running, done or failed) and, once it is done, its result: its headline, counts, depth, findings and the link to its signed evidence package. Use the check id that submit_claim_bundle returned.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_definitionsHow the person's workspace defines its terms (each with its version, owner and the date it took effect).No findings
Why it is in this group
- The name "get_definitions" says "get": a word for reading.
Description, as the server wrote it How the person's workspace defines its terms (each with its version, owner and the date it took effect). Give the definition as it is; do not change it.
Annotations the server declares
- 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 private-data.
- Reads private data0
- 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 out2
- 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 16, 2026, 14:20 UTC, unchanged since Nov 9, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 401
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- yes
- resource_metadata in WWW-Authenticate
- https://api.sternly.ai/.well-known/oauth-protected-resource/mcp
- RFC 9728 protected resource metadata
- https://api.sternly.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://clerk.sternly.ai
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- yes
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 verify https://api.sternly.ai/mcpclaude mcp add --transport http verify https://api.sternly.ai/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__verify__get_check",
"mcp__verify__get_definitions"
],
"ask": [
"mcp__verify__submit_claim_bundle",
"mcp__verify__propose_definitions"
],
"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 verify. Review it before you use it.
Capability tags behind 2 rules
- mcp__verify__submit_claim_bundle untrusted-input, outbound
- mcp__verify__propose_definitions outbound
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.sternly/verify/verify?hash=8c0d417508a0f8902353dfb88662214b4be1c8ffc0487e23c3a4e93571f033dc" | jq -e '.changed == false'Pinned hash 8c0d417508a0, from Nov 8, 2026, 13:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.sternly/verify/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.sternly/verify)Source: MCP Registry. Synced Nov 8, 2026, 13:17 UTC.
Sternly MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Sternly MCP server safe?
- No scan can promise that. What its definitions show: 4 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 Sternly MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Sternly MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: propose_definitions.
What tools does the Sternly MCP server have?
- 4 tools: 1 irreversible, 1 write, 2 read. propose_definitions, submit_claim_bundle, get_check and get_definitions.
Does the Sternly MCP server need sign-in or OAuth?
- Yes. Its remote endpoint answered 401 without credentials, and it publishes OAuth protected resource metadata (RFC 9728).
Does the Sternly 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): submit_claim_bundle and propose_definitions.
Has the Sternly MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.