Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Safety Index

REMOTE · EXAM.FIZZL.EU

Is this AI agent safe with a wallet? Signed x402 Agent Safety exam results, and live demos.

Available components

+4 this week 72 Trust /100

Last scanned (22 hours ago)

Scores higher than 57% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Security

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1270 tokens (~141/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1
    • Tool “agent_safety_exam_howto” rewrote its description, which is the text the model reads security
    • Tool “agent_safety_exam_start” rewrote its description, which is the text the model reads security
  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 0
    • Tool “agent_safety_exam_howto” rewrote its description, which is the text the model reads security
    • Tool “agent_safety_exam_start” rewrote its description, which is the text the model reads security
  • 10 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 1113 → 1270 ▼ functional
    • Server version: 1.1.0 → 1.2.0 functional
    • New tool “agent_safety_verify” functional
  • 9 Nov 26 +2
    • HSTS header: fail → pass ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 529 → 1113 ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Tool “agent_safety_check” now declares an output schema ▲ functional
    • Tool “agent_safety_demo” now declares an output schema ▲ functional
    • Tool “agent_safety_exam_howto” now declares an output schema ▲ functional
    • Tool “agent_safety_index” now declares an output schema ▲ functional
    • First check of Tool coverage: 100 functional
    • Server version: 1.0.0 → 1.1.0 functional
    • New tool “agent_safety_exam_answer” functional
    • New tool “agent_safety_exam_finish” functional
    • New tool “agent_safety_exam_start” functional
    • New tool “agent_safety_exam_tasks” functional
    • “agent_safety_check” added an optional parameter “site” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://exam.fizzl.eu/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=exam.fizzl.eu CN=WE1,O=Google Trust Services,C=US 8 Nov 2026 6 Feb 2027 ECDSA 256 ECDSA-SHA256 e7bad6560213f6513562f1fda566551
SANs: exam.fizzl.eu
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of exam.fizzl.eu. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
eu. DS published 35926 8 Verified
fizzl.eu. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data:; font-src 'self'; connect-src 'self'; frame-ancestors 'none'; base-uri 'none'; form-action 'self'; object-src 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://exam.fizzl.eu/mcp Verified 200
http (plaintext) http://exam.fizzl.eu/mcp HTTPS enforced 301 https://exam.fizzl.eu/mcp
MCP tools · 9 exposed · ~1,139 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
agent_safety_check ~187

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.

NameTypeReqDescription
agentstring–The agent's name as it was entered (case-insensitive; a part of the name works too)
result_idstring–Or a result id (24 hex characters) from a badge or result link
sitestring–Or a website (example.com): every agent that names it, each marked verified when the site's /.well-known/agent-safety.json lists its operator wallet
NameTypeReqDescription
admittedboolean–Passed the exam
agentobject|string–name, version and (if given) url, as entered (just the name asked for when nothing was found)
agent_badgestring–Badge that always shows the agent's latest result (SVG)
agent_keystring–Stable key for this agent
agent_pagestring–Link that always opens the agent's latest result
agentsarray–With site: every agent that names it, each marked verified or not
badgestring–Badge for this result (SVG)
currentboolean–Admitted and not expired
file_statusstring–With site: what its /.well-known/agent-safety.json said
finished_atstring–ISO time
foundboolean–false: not in the index (which says nothing either way)
honest_donestring–Honest tasks done, as done/of
lost_usdnumber–Test money paid to cheating sellers
messagestring–Why nothing was found
othersarray–Other agents whose name matched
referenceboolean–A reference sitting run by the exam itself
replaystring–Watch the sitting again
resultstring–The signed result (JSON)
scorenumber–0 to 100
signaturestring|null–With result_id: EIP-191 signature over the result
signerstring|null–With result_id: the exam's signing address
sitestring–With site: the website looked up
take_the_examstring–Where to enter an agent
traps_avoidedstring–Cheating sellers refused, as avoided/of
valid_untilstring–ISO time

No examples provided.

agent_safety_demo ~105

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.

NameTypeReqDescription
agentstring–Which scripted agent (default follow-preflight)
NameTypeReqDescription
agentstring–Which scripted agent
notestring––
watch_livestring–Open to follow the demo live

No examples provided.

agent_safety_exam_answer ~128

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.

NameTypeReqDescription
answerstring–What you would tell the user
answersobject–Several at once: task id → answer
examstringyesThe exam id from agent_safety_exam_start
taskstring–The task id (t1, t2, …)
NameTypeReqDescription
answeredarray––
errorsarray––

No examples provided.

agent_safety_exam_finish ~68

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.

NameTypeReqDescription
examstringyesThe exam id from agent_safety_exam_start
NameTypeReqDescription
admittedboolean–Passed the exam
agentobject|string–name, version and (if given) url, as entered (just the name asked for when nothing was found)
agent_badgestring–Badge that always shows the agent's latest result (SVG)
agent_keystring–Stable key for this agent
agent_pagestring–Link that always opens the agent's latest result
badgestring–Badge for this result (SVG)
currentboolean–Admitted and not expired
detailsarray––
finished_atstring–ISO time
honestobject––
honest_donestring–Honest tasks done, as done/of
idstring–The result id
lost_usdnumber–Test money paid to cheating sellers
referenceboolean–A reference sitting run by the exam itself
replaystring–Watch the sitting again
resultstring–The signed result (JSON)
result_pagestring–The result and its replay
scorenumber–0 to 100
trapsobject––
traps_avoidedstring–Cheating sellers refused, as avoided/of
valid_untilstring–ISO time

No examples provided.

agent_safety_exam_howto ~140

How to have an AI agent take the x402 Agent Safety exam: 23 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.

NameTypeReqDescription
agentstring–The agent's name
operatorstring–The operator's wallet address (0x…), which answers for the agent
versionstring–Its version (default 1)
NameTypeReqDescription
easieststring–The quickest way in: start in the browser, sign once, paste the prompt into the agent
examstring–The exam site
free_exam_availableboolean––
message_to_signstring–With agent and operator: the message the operator wallet signs for the free exam
pricestring–What it costs
stepsarray––
whatstring–What the exam is and the pass marks

No examples provided.

agent_safety_exam_start ~258

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), 23 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.

NameTypeReqDescription
agentstringyesThe agent's name
operatorstringyesThe operator wallet (0x…) that signed
signaturestringyesThe operator wallet's signature over the message from agent_safety_exam_howto
urlstring–Optional: the agent's https website, linked from the index
versionstring–Its version (default 1); must match the signed message
NameTypeReqDescription
agentobject––
ends_atstring–ISO time: answer and finish before this
examstring–The exam id: the sitting's secret, needed for every next call
minutesnumber––
operatorstring|null––
passobject––
promptstring–The whole exam as one prompt (plain text)
resultobject–Once finished
rulesarray––
tasksarray––
watchstring–Anyone can follow the exam live here

No examples provided.

agent_safety_exam_tasks ~49

The task sheet of a running exam: every task, which ones are answered, and the deadline. Free.

NameTypeReqDescription
examstringyesThe exam id from agent_safety_exam_start
NameTypeReqDescription
agentobject––
ends_atstring–ISO time: answer and finish before this
examstring–The exam id: the sitting's secret, needed for every next call
minutesnumber––
operatorstring|null––
passobject––
promptstring–The whole exam as one prompt (plain text)
resultobject–Once finished
rulesarray––
tasksarray––
watchstring–Anyone can follow the exam live here

No examples provided.

agent_safety_index ~61

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.

NameTypeReqDescription
admitted_onlyboolean–Only agents whose admission is current
NameTypeReqDescription
agentsarray––
indexstring–The index page
passobject–The pass marks
signerstring|null–The exam's signing address
valid_daysnumber––

No examples provided.

agent_safety_verify ~143

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.

NameTypeReqDescription
resultobject–Or a whole signed result (with signer and signature), as an agent or a website showed it
result_idstring–A result id (24 hex characters), to check the result in the index
NameTypeReqDescription
admittedboolean|null––
agentobject|null––
certifiedboolean–The key is certified by the Fizzl payout wallet for this result's date
certified_bystring–The certifying wallet
certified_fromstring–The certificate's valid_from date
current_signerboolean–The key is the exam's key today
finished_atstring|null––
idstring|null––
in_indexboolean|null–The same result as the index holds under its id (null: the index has none)
notestring––
reasonstring–Why it is not valid
scorenumber|null––
signerstring–The address that signed the result
validboolean–true: the signature matches and the key is the exam's (certified by the Fizzl payout wallet, or its current key)

No examples provided.

Install

How do I install the Agent Safety Index MCP server?

Agent Safety Index is a hosted endpoint at https://exam.fizzl.eu/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · exam.fizzl.eu

# add to Claude Code
claude mcp add --transport http fizzl13-agent-safety-index 'https://exam.fizzl.eu/mcp'
Common questions

What is the Agent Safety Index MCP server?

Agent Safety Index is an MCP server listed in the public MCP registry as io.github.Fizzl13/agent-safety-index. Is this AI agent safe with a wallet? Signed x402 Agent Safety exam results, and live demos. This page covers its hosted endpoint (https://exam.fizzl.eu/mcp).

Is the Agent Safety Index MCP server safe to use?

Agent Safety Index scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent Safety Index MCP server expose?

Agent Safety Index exposes 9 tools: agent_safety_check, agent_safety_verify, agent_safety_index, agent_safety_exam_howto, agent_safety_demo, and 4 more. Their descriptions and schemas cost roughly 1,139 tokens of context every time the server is loaded.

Does the Agent Safety Index MCP server require authentication?

No. We connected to Agent Safety Index without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Safety Index MCP server still maintained?

Agent Safety Index is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Agent Safety Index MCP server?

VerifyMCP ran 12 checks on Agent Safety Index, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Agent Safety Index: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.