makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server
ai.makememoneynomistakes/scoreboardmakememoneynomistakes.aistreamable-httpv1.1.0Scanned
Check before you hire or pay an ERC-8004 agent on Base: track record, reputation and fraud flags.
19 tools: 14 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
14 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 makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server can do
The makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server is published by makememoneynomistakes.ai, a domain the MCP Registry verified. It has 19 tools. It can create or change data (14 tools: pathways_report, pathways_session, pathways_plan, check_agent and 10 more), but cannot delete data. 5 tools only read.
1 tool brings in text other people can write (bouncer_log).
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, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.1.0.
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.
19 tools
Changes things 14Claude Code: ask
buy_passFor heavy use, a call bundle: $1 in USDC on Base over x402 for 500 calls within 4 hours, the same $0.002 a call settled once and nothing more to sign (pages past 25 cost 1, longer …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 For heavy use, a call bundle: $1 in USDC on Base over x402 for 500 calls within 4 hours, the same $0.002 a call settled once and nothing more to sign (pages past 25 cost 1, longer log pages 3, the export 25). Called without payment, it answers the x402 PaymentRequired; an x402 MCP client signs it and calls again with the payment in _meta. Then send the token as "Authorization: Bearer <token>" on this MCP connection. No account, no refunds; unused calls expire.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
check_agentCheck before you hire or pay an ERC-8004 agent on Base: its track record and fraud check in one call.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 before you hire or pay an ERC-8004 agent on Base: its track record and fraud check in one call. Returns the verdict (LEGIT, SUS or BOUNCED: honesty), a 0-100 score from paid escrow work and clean reviews (quality; null when bounced or no clean record), fraud flags with onchain receipts, and stats. When activated, paid_per_use separately reports the payer-only score and stats; category labels and risk notes never affect scores. Use it for due diligence before you delegate work, send an x402 payment or trust an agent's reviews. Read the verdict first. Takes an id (base:14516, moltlaunch:0x…); call find_agent first if you only have a name or a wallet. Free within the per-IP allowance.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
exportBulk reputation data for ERC-8004 agents on Base: every agent's scorecard (with enhanced descriptions where researched) plus the full Bouncer's log in one response (about 1 MB): bu…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 Bulk reputation data for ERC-8004 agents on Base: every agent's scorecard (with enhanced descriptions where researched) plus the full Bouncer's log in one response (about 1 MB): build your own index, backtest a hiring rule, or check many agents for less than 26 single calls. Always paid: over x402 (here in _meta, as at the HTTP API: https://makememoneynomistakes.ai/skill.md), or a pass covers it for 25 calls.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
outcomesAfter you hire: for each agent you checked with track on, your escrow jobs with it since the check: no_hire_yet, in_progress, completed, disputed or refunded.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 After you hire: for each agent you checked with track on, your escrow jobs with it since the check: no_hire_yet, in_progress, completed, disputed or refunded. Needs a pass. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
pathways_authorizeStep 4 of Open Commerce Pathways: authorize one AI planning run by our default compute agent, $0.02 in USDC on Base over x402, usable within 1 hour.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 Step 4 of Open Commerce Pathways: authorize one AI planning run by our default compute agent, $0.02 in USDC on Base over x402, usable within 1 hour. Called without payment, it answers the x402 PaymentRequired; your x402 MCP client signs it with your own wallet and calls again with the payment in _meta. Returns a token for pathways_run. A run that fails on our side gives it back; no refunds otherwise. A call bundle does not cover it.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
pathways_delegatesDelegated compute (open beta): the trusted x402 compute sellers you can hand your heavy work to, with the exact call, and how your budget splits (our fee a flat $0.01 per session; …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 Delegated compute (open beta): the trusted x402 compute sellers you can hand your heavy work to, with the exact call, and how your budget splits (our fee a flat $0.01 per session; up to half of the rest for one compute seller; the remainder for data routes). A seller fits when it is a current route serving LLM and AI, its seller has a Paid per use score of 40+, we can fill its declared input, it is not a financial or trading service, and it costs at most the delegate share and $1. Put your prompt where "<your prompt>" is; we set the length. The first is the one we propose. We never call or pay a seller: your own wallet pays it directly. Budget 0.50 to 35 USDC. Free within the per-IP allowance, then $0.002. Live data only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
pathways_ledgerStep 6 of Open Commerce Pathways: the real money in and out of the wallet that paid for your x402 compute runs, from Base USDC transfers we scan onchain since its first run.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 Step 6 of Open Commerce Pathways: the real money in and out of the wallet that paid for your x402 compute runs, from Base USDC transfers we scan onchain since its first run. Income counts only x402 (EIP-3009) payments to that wallet; plain transfers in are deposits. Spend is split into our fees, route sellers and other; spend.planned_usdc and income.planned_usdc are the planned line (purchases a Pathways plan issued, and x402 sales after the first of them). profit is true only when coverage is current and net_planned_usdc is positive; net_usdc is the whole wallet. Free within the per-IP allowance, then $0.002. Live data only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
pathways_planReserve at most 10 x402 data calls and one delegate call in a paid session.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 Reserve at most 10 x402 data calls and one delegate call in a paid session. Shows the default prompt and exact calls from our current directory. Re-reading preserves the same allowances. Report an actual delegate failure with failed_call for one retry within the remaining share, or fallback=true for our one fallback attempt. No fallback after the persistent five-failure pause. Report success with succeeded_call and success_tx; its Base USDC receipt is verified before resetting the failure count. The plan holds your routes plus up to 5 ranked routes on other hosts within the data share (plan.routes_added); second_pass=true after a data call came back with values reserves one more call to it within the share.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
pathways_promptStep 3 of Open Commerce Pathways: the default planning prompt for the x402 pathway you chose (one route resells it, two to five bundle them), shown in full before anything runs, wi…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 Step 3 of Open Commerce Pathways: the default planning prompt for the x402 pathway you chose (one route resells it, two to five bundle them), shown in full before anything runs, with the compute terms. Edit it if you like, authorize one run with pathways_authorize, then call pathways_run. Free within the per-IP allowance, then $0.002. Live data only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
pathways_reportVerify your x402 session purchases and write one report from their Base USDC receipts, the ledger, and at most 8000 characters of untrusted delegate output.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 Verify your x402 session purchases and write one report from their Base USDC receipts, the ledger, and at most 8000 characters of untrusted delegate output. Supply at most 12 payments with issued call IDs. Receipts prove transfers, not useful work. Includes actual costs against shares, an attributed output summary, ledger state and a next step. Included in the session fee; no new payment. One report attempt per session.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
pathways_routesStep 1 of Open Commerce Pathways: the paid x402 routes your budget can afford, only from sellers our data clears (LEGIT on both boards, 5+ independent paying customers, verified id…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 Step 1 of Open Commerce Pathways: the paid x402 routes your budget can afford, only from sellers our data clears (LEGIT on both boards, 5+ independent paying customers, verified identity, one Base USDC recipient). Each route has its cost, recipient, how many calls the budget buys, the seller's evidence, the use it serves and fit (why it ranks where it does: a known resale margin and no empty answer in our relay history first; a route whose last bought answer came back empty last, not recommended); filter by use. Then pick routes for pathways_list. We recommend only: your own wallet approves and pays any call you make. Free within the per-IP allowance, then $0.002. Live data only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
pathways_runStep 5 of Open Commerce Pathways: spends one run authorized with pathways_authorize and plans your x402 pathway on our AI model, from our trust and market data.No findings
Why it is in this group
- The name "pathways_run" says "run": a word for a change.
Description, as the server wrote it Step 5 of Open Commerce Pathways: spends one run authorized with pathways_authorize and plans your x402 pathway on our AI model, from our trust and market data. Returns the plan and the exact next x402 calls (from our data, not the model): your own wallet approves and pays each one, straight to the seller. A plan, not advice or a promise of income. Live data only.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
pathways_sessionBuy a one-hour session over x402.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 Buy a one-hour session over x402. Budget 0.50 to 35 USDC; our fee is a flat 0.01 USDC per session. The rest stays in your wallet, split between a delegate and data routes. Returns a token for pathways_plan. Your wallet signs each purchase; a call bundle does not cover a session.
Annotations the server declares
- readOnlyHint: false
- openWorldHint: false
statsBoard-wide reputation numbers for ERC-8004 agents on Base over the 30-day window: agents scored, ranked, rookies, bounced, farm raters, share of reviews farmed.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 Board-wide reputation numbers for ERC-8004 agents on Base over the 30-day window: agents scored, ranked, rookies, bounced, farm raters, share of reviews farmed. Free within the per-IP allowance.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 5Show 5 read-only tools
bouncer_logThe fraud log for ERC-8004 agents on Base: hard and soft flags (self-hires, payment loops, shared funders, bursts, review farms) plus coordinated reviewer cohorts, newest first, wi…Reads text others writeNo findings
Why it is in this group
- The name "bouncer_log" says "log": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it The fraud log for ERC-8004 agents on Base: hard and soft flags (self-hires, payment loops, shared funders, bursts, review farms) plus coordinated reviewer cohorts, newest first, with onchain receipts. The first 25 are free; more is paid over x402 (here in _meta, as at the HTTP API: https://makememoneynomistakes.ai/skill.md), or a call-bundle pass covers it.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
find_agentFind an ERC-8004 agent on Base by name, wallet address or part of its id, when you don't have its exact id: the first step of a reputation check.No findings
Why it is in this group
- The name "find_agent" says "find": a word for reading.
Description, as the server wrote it Find an ERC-8004 agent on Base by name, wallet address or part of its id, when you don't have its exact id: the first step of a reputation check. Up to 10 matches, best first, each with verdict, score and flag count; then call check_agent with the id for the full scorecard. Free within the per-IP allowance.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
find_servicesBefore you pay an x402 service, see whether it belongs to an agent with a track record: paid x402 services we observed on Coinbase's x402 Bazaar, with coverage.No findings
Why it is in this group
- The name "find_services" says "find": a word for reading.
Description, as the server wrote it Before you pay an x402 service, see whether it belongs to an agent with a track record: paid x402 services we observed on Coinbase's x402 Bazaar, with coverage. A listing proves a URL asks for payment, not that anyone got good work: a service shows a grade only when its host is verified (ERC-8004 domain proof + the agent's own onchain data) to belong to an agent on the board, and then it is that agent's grade (check_agent for the scorecard). Everything else is ungraded with a reason. Filter by host, agent or coverage state. Free within the per-IP allowance. Live data only.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_agentsCompare ERC-8004 agents on Base by reputation: a page with score, verdict and flag count, to shortlist whom to hire or grade a whole category.No findings
Why it is in this group
- The name "list_agents" says "list": a word for reading.
Description, as the server wrote it Compare ERC-8004 agents on Base by reputation: a page with score, verdict and flag count, to shortlist whom to hire or grade a whole category. Hired filters: ranked, rookies. Paid per use filters: paid_per_use, paid_per_use_rookies (payer evidence only, basis paid_calls). One bouncer filter for SUS/BOUNCED. Separate paid_per_use stats and category labels never overwrite Hired job/ETH fields. The first 25 without a cursor are free; more, or the next page, is paid over x402 (here in _meta, as at the HTTP API: https://makememoneynomistakes.ai/skill.md), or a call-bundle pass covers it.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
pathways_listStep 2 of Open Commerce Pathways: ways to make money with 1 to 5 paid x402 routes you picked from pathways_routes.No findings
Why it is in this group
- The name "pathways_list" says "list": a word for reading.
Description, as the server wrote it Step 2 of Open Commerce Pathways: ways to make money with 1 to 5 paid x402 routes you picked from pathways_routes. Each pathway (resell one route, or bundle several) shows the market it sells into from the whole x402 Bazaar (resources, sellers, sellers we trust, reported calls and payers in 30 days, typical cost), your unit cost, the margin at the typical cost and the sales needed to recover your budget. Measured figures only, no expected returns; demand figures are provider-reported. Free within the per-IP allowance, then $0.002. Live data only.
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 outbound.
- 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 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, 18:26 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
- 14
- 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 14 tools that change things (14 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://makememoneynomistakes.ai/mcp: tools/list returned 19 tools to an anonymous client, including pathways_report (write), pathways_session (write), pathways_plan (write), check_agent (write), pathways_routes (write) and 9 more
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.
Tools2 changed.~2 changedView diff
- Changed:pathways_ledgerChanges thingsdescription
- Changed:pathways_planChanges thingsdescriptioninputSchema
Tools6 changed.~6 changedView diff
- Changed:buy_passChanges thingsdescription
- Changed:exportChanges thingsdescription
- Changed:list_agentsOnly readsdescription
- Changed:pathways_delegatesChanges thingsdescription
- Changed:pathways_routesChanges thingsdescription
- Changed:pathways_sessionChanges thingsdescription
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http scoreboard https://makememoneynomistakes.ai/mcpclaude mcp add --transport http scoreboard https://makememoneynomistakes.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__scoreboard__find_agent",
"mcp__scoreboard__find_services",
"mcp__scoreboard__pathways_list",
"mcp__scoreboard__list_agents",
"mcp__scoreboard__bouncer_log"
],
"ask": [
"mcp__scoreboard__pathways_report",
"mcp__scoreboard__pathways_session",
"mcp__scoreboard__pathways_plan",
"mcp__scoreboard__check_agent",
"mcp__scoreboard__pathways_routes",
"mcp__scoreboard__pathways_delegates",
"mcp__scoreboard__pathways_prompt",
"mcp__scoreboard__pathways_authorize",
"mcp__scoreboard__pathways_run",
"mcp__scoreboard__pathways_ledger",
"mcp__scoreboard__stats",
"mcp__scoreboard__export",
"mcp__scoreboard__outcomes",
"mcp__scoreboard__buy_pass"
],
"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 scoreboard. Review it before you use it.
Capability tags behind 1 rule
- mcp__scoreboard__bouncer_log 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/ai.makememoneynomistakes/scoreboard/verify?hash=481f9b6d3cb01d9a30ff8639eced8657bfa50ef6ca5f56a24785818632a44d7d" | jq -e '.changed == false'Pinned hash 481f9b6d3cb0, from Nov 11, 2026, 20:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.makememoneynomistakes/scoreboard/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.makememoneynomistakes/scoreboard)Source: MCP Registry. Synced Oct 21, 2026, 17:42 UTC.
makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server safe?
- No scan can promise that. What its definitions show: 19 tools, 14 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 makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks 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 makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server have?
- 19 tools: 14 write, 5 read. pathways_report, pathways_session, pathways_plan, check_agent, pathways_routes, pathways_delegates, pathways_prompt, pathways_authorize and 11 more.
Does the makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the makememoneynomistakes.ai: ERC-8004 agent reputation and fraud checks MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.