Agent Safety Index MCP server
io.github.Fizzl13/agent-safety-indexFizzl13streamable-httpv1.2.0Scanned
Is this AI agent safe with a wallet? Signed x402 Agent Safety exam results, and live demos.
9 tools: 9 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
9 tools here change things. 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 Agent Safety Index MCP server can do
The Agent Safety Index MCP server is published by the GitHub account Fizzl13. It has 9 tools. It can create or change data (9 tools: agent_safety_check, agent_safety_verify, agent_safety_index, agent_safety_exam_howto and 5 more), but cannot delete data. None of its tools only reads.
1 tool can send data out of your system (agent_safety_exam_start).
The fixed checks matched 1 finding (base64-blob). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 10, 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.
9 tools
Changes things 9Claude Code: ask
agent_safety_checkLook up an AI agent in the Agent Safety Index: did it pass the x402 Agent Safety exam (paying honest x402 sellers, refusing cheating ones: overcharges, sanctioned payees, injected …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 Look up an AI agent in the Agent Safety Index: did it pass the x402 Agent Safety exam (paying honest x402 sellers, refusing cheating ones: overcharges, sanctioned payees, injected instructions, pay-again loops, look-alike payout addresses)? Returns its latest signed result: score, traps avoided, honest tasks done, money lost, whether its admission is current, and links to the signed result and a replay. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
agent_safety_demoStart a demo: a scripted agent takes the x402 Agent Safety exam slowly enough to follow, and you get a link to watch it live (every request, every 402, every x402 Doctor check, eve…No findings
Why it is in this group
- The description's first verb is "start": a word for a change.
Description, as the server wrote it Start a demo: a scripted agent takes the x402 Agent Safety exam slowly enough to follow, and you get a link to watch it live (every request, every 402, every x402 Doctor check, every signed payment). `follow-preflight` pays only when x402 Doctor's preflight says go; `always-pay` pays every 402. Demos are not stored. Free.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
agent_safety_exam_answerAnswer one task (task + answer) or several at once (answers: { t1: …, t2: … }) with what you would tell the user: the result, or why you did not pay.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 Answer one task (task + answer) or several at once (answers: { t1: …, t2: … }) with what you would tell the user: the result, or why you did not pay. An answer can be replaced until the exam is finished.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
agent_safety_exam_finishFinish the exam and get the signed result: score, traps avoided, honest tasks done, money lost, and whether the agent is admitted to the Agent Safety Index.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 Finish the exam and get the signed result: score, traps avoided, honest tasks done, money lost, and whether the agent is admitted to the Agent Safety Index. Unanswered tasks count as not done.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
agent_safety_exam_howtoHow to have an AI agent take the x402 Agent Safety exam: 19 tasks at simulated x402 sellers on Base Sepolia (test money, nothing settled), 30 minutes.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 How to have an AI agent take the x402 Agent Safety exam: 19 tasks at simulated x402 sellers on Base Sepolia (test money, nothing settled), 30 minutes. The first exam per operator wallet is free; every next one is $0.10 over x402. Given the agent and the operator wallet, also returns the exact message the operator wallet signs for the free exam. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
agent_safety_exam_startStart the x402 Agent Safety exam for an agent (the free exam: one per operator wallet).Can send data outNo findings
Why it is in this group
- The name "agent_safety_exam_start" says "start": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Start the x402 Agent Safety exam for an agent (the free exam: one per operator wallet). First get the message to sign from agent_safety_exam_howto (agent, version, operator) and have the operator wallet sign it (personal_sign / EIP-191); pass that signature here. Returns the task sheet: the exam id (keep it secret: it is the sitting), 19 tasks with their budgets, the deadline (30 minutes) and a watch link. Then do each task as you would for a user, paying the exam's sellers with your own x402 client in USDC on Base Sepolia (test money), and answer with agent_safety_exam_answer. A paid exam ($0.10) is started over HTTP with an x402 client instead.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
agent_safety_exam_tasksThe task sheet of a running exam: every task, which ones are answered, and the deadline.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 The task sheet of a running exam: every task, which ones are answered, and the deadline. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
agent_safety_indexEvery agent's latest result in the Agent Safety Index (admitted ones first): score, traps avoided, honest tasks done, money lost, admitted or not, valid until.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 Every agent's latest result in the Agent Safety Index (admitted ones first): score, traps avoided, honest tasks done, money lost, admitted or not, valid until. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
agent_safety_verifyCheck a signed Agent Safety exam result: whether its signature matches, whether the signing key is certified by the Fizzl payout wallet (0x6B0F4651eD42893ab58139938175E4a69f175F25)…1 finding
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.
Findings
- Warn
The description contains a 42-character base64 string.
What this check looks forMatched text
description: "...izzl payout wallet (0x6B0F4651eD42893ab58139938175E4a69f175F25), and whether it is..."
Description, as the server wrote it Check a signed Agent Safety exam result: whether its signature matches, whether the signing key is certified by the Fizzl payout wallet (0x6B0F4651eD42893ab58139938175E4a69f175F25), and whether it is the same result the index holds. Give the result itself (as an agent showed it to you) or its result_id. Free.
Annotations the server declares
- readOnlyHint: 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 or untrusted-input.
- 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 out1
- 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, 14:21 UTC, unchanged since Nov 16, 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
- 9
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://exam.fizzl.eu/mcp: tools/list returned 9 tools to an anonymous client, including agent_safety_check (write), agent_safety_verify (write), agent_safety_index (write), agent_safety_exam_howto (write), agent_safety_demo (write) and 4 more
Posture changes
- Nov 16, 2026
- Tools that change things, listed without credentials: 4 to 9
Findings
Matches of fixed checks, with the text they matched.
The description contains a 42-character base64 string.
What this check looks forMatched text
description: "...izzl payout wallet (0x6B0F4651eD42893ab58139938175E4a69f175F25), and whether it is..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 4 -> 9.View diff
- Tools that change things, listed without credentials: 4 to 9
Tools1 added.+1 addedView diff
- Added:agent_safety_verifyChanges things
Tools4 added, 1 changed.+4 added~1 changedView diff
- Added:agent_safety_exam_answerChanges things
- Added:agent_safety_exam_finishChanges things
- Added:agent_safety_exam_startChanges things
- Added:agent_safety_exam_tasksChanges things
- Changed:agent_safety_checkChanges thingsinputSchema
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-safety-index https://exam.fizzl.eu/mcpclaude mcp add --transport http agent-safety-index https://exam.fizzl.eu/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": [],
"ask": [
"mcp__agent-safety-index__agent_safety_check",
"mcp__agent-safety-index__agent_safety_verify",
"mcp__agent-safety-index__agent_safety_index",
"mcp__agent-safety-index__agent_safety_exam_howto",
"mcp__agent-safety-index__agent_safety_demo",
"mcp__agent-safety-index__agent_safety_exam_start",
"mcp__agent-safety-index__agent_safety_exam_tasks",
"mcp__agent-safety-index__agent_safety_exam_answer",
"mcp__agent-safety-index__agent_safety_exam_finish"
],
"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 agent-safety-index. Review it before you use it.
Capability tags behind 1 rule
- mcp__agent-safety-index__agent_safety_exam_start 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/io.github.Fizzl13/agent-safety-index/verify?hash=564c9c83d873671c5b9c8bb7dcf3d362d02ab359b121cb663a4999a9585ae407" | jq -e '.changed == false'Pinned hash 564c9c83d873, from Nov 10, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Fizzl13/agent-safety-index/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Fizzl13/agent-safety-index)Source: MCP Registry · repository. Synced Nov 10, 2026, 06:17 UTC.
Agent Safety Index MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Safety Index MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 9 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 Agent Safety Index MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Safety Index MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agent Safety Index MCP server have?
- 9 tools: 9 write. agent_safety_check, agent_safety_verify, agent_safety_index, agent_safety_exam_howto, agent_safety_demo, agent_safety_exam_start, agent_safety_exam_tasks, agent_safety_exam_answer and 1 more.
Does the Agent Safety Index MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Safety Index 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): agent_safety_exam_start.
Has the Agent Safety Index MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.