safe4 MCP server
ai.safe4/safe4safe4.aistreamable-httpv1.0.0Scanned
Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.
2 tools: 1 do something that can't be undone and 1 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
2 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the safe4 MCP server can do
The safe4 MCP server is published by safe4.ai, a domain the MCP Registry verified. It has 2 tools. It can do things that cannot be undone, such as sending, paying or publishing (safe4_authorize) and create or change data (1 tool: safe4_price), but cannot delete data. None of its tools only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 28, 2026, version 1.0.0.
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.
2 tools
Can't be undone 1Claude Code: ask
safe4_authorizeDecide whether a proposed agent payment should proceed.No findings
Why it is in this group
- The input carries an amount (input.amount) and a currency, so it moves money.
Description, as the server wrote it Decide whether a proposed agent payment should proceed. Settled per call in USDC over x402. Called without ``payment`` it returns the price list rather than a decision; call it again with the signed payload to receive one. The task and the two allow-lists are the principal's constraints, not the agent's: they are what the purchase is tested against, so an agent that writes its own ``task`` is grading its own homework. Safe4 records every field it was given in the audit entry and marks the task context as request-supplied, so a substituted constraint is visible afterwards. Args: task: The task the agent was given, as stated by its principal. purchase: What is being bought. purchase_purpose: Why this purchase serves the task. amount: Decimal amount as a string, for example "25.00". currency: Currency of the proposed payment, for example "USDC". counterparty: Who would receive the payment. service_category: Category of the thing being bought. allowed_service_categories: Categories the principal permits. allowed_counterparties: Optional payees the principal permits. When supplied, payment to anyone else is denied. task_id: Optional caller-side task identifier, echoed into the audit. payment: An x402 payment payload for this call. Omit to receive the price list instead of a decision.
Changes things 1Claude Code: ask
safe4_pricePrice and accepted payment networks for one Safe4 decision.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.
Description, as the server wrote it Price and accepted payment networks for one Safe4 decision. Free to call. Returns the same x402 terms the HTTP endpoint advertises, so an agent can see the cost before committing to a paid call.
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.
Looked at Nov 20, 2026, 18:27 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: initialize answered HTTP 404.
Posture changes
- Nov 13, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
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.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 2 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http safe4 https://api.safe4.ai/mcp/claude mcp add --transport http safe4 https://api.safe4.ai/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.
{
"permissions": {
"allow": [],
"ask": [
"mcp__safe4__safe4_price",
"mcp__safe4__safe4_authorize"
],
"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 safe4. 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.safe4/safe4/verify?hash=43724ec92ab29b5c55c52c57ceb0556d5848b76f0d0805eec176d91901fd10f5" | jq -e '.changed == false'Pinned hash 43724ec92ab2, from Oct 28, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.safe4/safe4/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.safe4/safe4)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:43 UTC.
safe4 MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the safe4 MCP server safe?
- No scan can promise that. What its definitions show: 2 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 safe4 MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the safe4 MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: safe4_authorize.
What tools does the safe4 MCP server have?
- 2 tools: 1 irreversible, 1 write. safe4_authorize and safe4_price.
Does the safe4 MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the safe4 MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the safe4 MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 28, 2026.