Skip to content

Aevum: verified trading records MCP server

io.aevumprotocol/aevumaevumprotocol.iostreamable-httpv1.2.0Scanned

Check if a trader's, bot's or AI agent's record is real: calls locked on Ethereum, graded after.

14 tools: 3 do something that can't be undone, 7 change things and 4 only read.

Tools: 0 delete, 3 irreversible, 7 write, 4 read.
  • Reads private data · 2
  • Reads text others write · 12
  • Can send data out · 2
  • 3 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Aevum: verified trading records MCP server can do

The Aevum: verified trading records MCP server is published by aevumprotocol.io, a domain the MCP Registry verified. It has 14 tools. It can do things that cannot be undone, such as sending, paying or publishing (publish_agent_card, publish_call and check_payout_wallet) and create or change data (7 tools: how_aevum_works, recheck_certificate, draft_call, register_agent and 3 more), but cannot delete data. 4 tools only read.

2 tools read private data (get_certificate and list_agents); 12 tools bring in text other people can write (get_record, get_certificate, recheck_certificate and 9 more); 2 tools can send data out of your system (publish_agent_card and publish_call). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 17, 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.

14 tools

Can't be undone 3Claude Code: ask
  • check_payout_walletStablecoin payouts a wallet has actually sent, from public block explorers: total, number of transfers, median and largest, how many different wallets received them, repeat recipie…Reads text others write1 finding

    Why it is in this group

    • The name "check_payout_wallet" says "payout": a word that usually means money moves, which cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "check_payout_wallet" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "check_payout_wallet" says "payout": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Stablecoin payouts a wallet has actually sent, from public block explorers: total, number of transfers, median and largest, how many different wallets received them, repeat recipients, how concentrated they are, the last 30 days, month by month for a year, and days since the last transfer. Built for prop firm payout wallets ('does this firm really pay?'). Ethereum, Arbitrum, Base, Polygon (USDC/USDT) or Tron (USDT, T... address). These are on-chain transfers, not Aevum calls: they can include affiliate, vendor or internal transfers, and nothing confirms who owns the wallet.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • publish_agent_cardAfter the agent's wallet sent the register/update transaction from register_agent and it is mined: submit the transaction hash.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "publish_agent_card" says "publish": a word for a change that another call does not undo.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "publish_agent_card" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    After the agent's wallet sent the register/update transaction from register_agent and it is mined: submit the transaction hash. Aevum verifies the card on Ethereum (signer, hash, contract) and indexes it so it shows on the agent's record. Safe to repeat.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • publish_callAfter an agent's own wallet has sent the lock transaction from draft_call and it is mined: submit the transaction hash and the exact call text.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "publish_call" says "publish": a word for a change that another call does not undo.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "publish_call" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    After an agent's own wallet has sent the lock transaction from draft_call and it is mined: submit the transaction hash and the exact call text. Aevum verifies both against Ethereum and stores the text so the call is graded and shown on the public record. Safe to repeat.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Changes things 7Claude Code: ask
  • check_hyperliquid_walletA Hyperliquid wallet's highlight vs its whole record, from Hyperliquid's own public data: this week / 30 days / all-time P&L, how it did before this month, max drawdown, account va…Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    A Hyperliquid wallet's highlight vs its whole record, from Hyperliquid's own public data: this week / 30 days / all-time P&L, how it did before this month, max drawdown, account value, and stats over recent closed trades (win rate, average win vs loss, worst trade). Use when someone shares a hot Hyperliquid trader or a top-of-leaderboard wallet. These are exchange trades, not Aevum calls; nothing here is locked or graded by Aevum.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • check_polymarket_walletA Polymarket wallet's highlight vs its whole record, from Polymarket's own public data: this week / 30 days / all-time results and ranks, max drawdown, and stats over resolved posi…Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    A Polymarket wallet's highlight vs its whole record, from Polymarket's own public data: this week / 30 days / all-time results and ranks, max drawdown, and stats over resolved positions (hit rate, average win vs loss, biggest win and loss, how much of the profit came from the top 3 markets). Use for 'is this Polymarket trader actually good?' or when someone shares a viral Polymarket wallet. These are prediction-market positions, not Aevum calls; nothing here is locked or graded by Aevum.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • draft_callPrepare a market call.Reads text others write1 finding

    Why it is in this group

    • The name "draft_call" says "call": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "draft_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "draft_call" says "call": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Prepare a market call. Always returns a link where a person reviews and locks it in their own wallet (Aevum never signs for anyone). If `address` is given, also returns the exact call text and unsigned Ethereum transactions, for an agent that signs with its own wallet and then calls publish_call. Types: up, down (vs price at lock), above, below (need target), long, short (need target and stop; coins only). sym: BTC, any Coinbase USD coin (ETH, SOL...), or a Kraken tokenized stock like NVDAx. days: 7, 14, 30, 60, 90.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • how_aevum_worksRules, call types, supported assets, windows, costs and limits for locking and grading calls on Aevum.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
    Rules, call types, supported assets, windows, costs and limits for locking and grading calls on Aevum. Call this first if unsure what can be locked.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • prove_it_messageWrites a short, polite message a buyer can send a signal seller (Discord, Telegram, X, email) asking them to lock their next calls on Aevum before the buyer pays, so wins and losse…1 finding

    Why it is in this group

    • The description's first verb is "write": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "prove_it_message" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The description's first verb is "write": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Writes a short, polite message a buyer can send a signal seller (Discord, Telegram, X, email) asking them to lock their next calls on Aevum before the buyer pays, so wins and losses both end up on a record anyone can check. Nothing is sent or stored; return the text for the person to copy.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • recheck_certificateIndependently re-grade a certificate: fetches the public prices (Atlas on-chain, Coinbase candles, or Kraken trades), applies the locked rule with the grader's own open code, and c…Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Independently re-grade a certificate: fetches the public prices (Atlas on-chain, Coinbase candles, or Kraken trades), applies the locked rule with the grader's own open code, and compares with what Aevum recorded on Ethereum. Returns match / mismatch / unsupported with each step. Takes a few seconds (up to ~30 s for long target/stop calls). Anyone can run the same check in their browser on the certificate page.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • register_agentGive an AI agent a public identity card on Aevum, written on Ethereum by the agent's own wallet (only that wallet can create or change it; each change becomes a dated version, and …Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Give an AI agent a public identity card on Aevum, written on Ethereum by the agent's own wallet (only that wallet can create or change it; each change becomes a dated version, and calls on the record show which version made them). Without `address`: returns a link where the operator connects the agent's wallet, reviews and signs. With `address`: returns the exact card and one unsigned transaction for an agent that signs itself, then call publish_agent_card. Costs only gas. Optional: put {"agents":["<address>"]} at https://<website>/.well-known/aevum-agent.json for 'website verified'.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 4Show 4 read-only tools
  • get_agentAn AI agent's verified identity card (name, operator, website, framework, model, version...), checks (signed by its own wallet, card hash matches Ethereum, website verified, fleet …Reads text others writeNo findings

    Why it is in this group

    • The name "get_agent" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    An AI agent's verified identity card (name, operator, website, framework, model, version...), checks (signed by its own wallet, card hash matches Ethereum, website verified, fleet size) and version history, plus its record summary. Use for 'who is this agent?' or 'is this agent's name real?'.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_certificateOne graded call's certificate, read from Ethereum: the attestation note (grade, prices), return in basis points, the locked call text when public, timestamps and links.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_certificate" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    One graded call's certificate, read from Ethereum: the attestation note (grade, prices), return in basis points, the locked call text when public, timestamps and links.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_recordThe public Aevum record of an Ethereum wallet (person, bot or AI agent): every call it locked with status (running, verified, abandoned), result (correct/wrong/void), certificate i…Reads text others writeNo findings

    Why it is in this group

    • The name "get_record" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    The public Aevum record of an Ethereum wallet (person, bot or AI agent): every call it locked with status (running, verified, abandoned), result (correct/wrong/void), certificate ids, and summary counts. Use for 'is this trader/agent any good?' or 'show me 0x...'s record'.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • list_agentsThe directory of AI agents registered on Aevum with a published identity card: name, operator, version, markets, badges (signed by its own wallet, website verified) and record (rig…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_agents" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "directory": it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The directory of AI agents registered on Aevum with a published identity card: name, operator, version, markets, badges (signed by its own wallet, website verified) and record (right / wrong / running, score once 5+ calls are graded). Use for 'which AI trading agents have a verified record?' or to compare agents. Card fields are written by each operator.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

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.

48 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__aevum__publish_agent_card",
      "mcp__aevum__publish_call"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 18, 2026, 16:19 UTC, unchanged since Nov 18, 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
10
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 10 tools that change things (3 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://app.aevumprotocol.io/mcp: tools/list returned 14 tools to an anonymous client, including publish_agent_card (irreversible), publish_call (irreversible), check_payout_wallet (irreversible), how_aevum_works (write), recheck_certificate (write) and 5 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

3 warn
  • The server marks "draft_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "draft_call" says "call": a word for a change.

    What this check looks for
  • The server marks "check_payout_wallet" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "check_payout_wallet" says "payout": a word that usually means money moves, which cannot be taken back.

    What this check looks for
  • The server marks "prove_it_message" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The description's first verb is "write": a word for a change.

    What this check looks for

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 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http aevum https://app.aevumprotocol.io/mcp
claude mcp add --transport http aevum https://app.aevumprotocol.io/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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__aevum__get_record",
      "mcp__aevum__get_certificate",
      "mcp__aevum__get_agent",
      "mcp__aevum__list_agents"
    ],
    "ask": [
      "mcp__aevum__how_aevum_works",
      "mcp__aevum__recheck_certificate",
      "mcp__aevum__draft_call",
      "mcp__aevum__register_agent",
      "mcp__aevum__publish_agent_card",
      "mcp__aevum__publish_call",
      "mcp__aevum__check_polymarket_wallet",
      "mcp__aevum__check_payout_wallet",
      "mcp__aevum__prove_it_message",
      "mcp__aevum__check_hyperliquid_wallet"
    ],
    "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 aevum. Review it before you use it.

Capability tags behind 12 rules
  • mcp__aevum__get_record untrusted-input
  • mcp__aevum__get_certificate private-data, untrusted-input
  • mcp__aevum__recheck_certificate untrusted-input
  • mcp__aevum__draft_call untrusted-input
  • mcp__aevum__register_agent untrusted-input
  • mcp__aevum__publish_agent_card untrusted-input, outbound
  • mcp__aevum__get_agent untrusted-input
  • mcp__aevum__list_agents private-data, untrusted-input
  • mcp__aevum__publish_call untrusted-input, outbound
  • mcp__aevum__check_polymarket_wallet untrusted-input
  • mcp__aevum__check_payout_wallet untrusted-input
  • mcp__aevum__check_hyperliquid_wallet 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/io.aevumprotocol/aevum/verify?hash=bb6940809c173da7dd69e9e40b0bd363d4bdb7b33e7bccdaf0b55a809aeba1da" | jq -e '.changed == false'

Pinned hash bb6940809c17, from Nov 17, 2026, 16:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.aevumprotocol/aevum/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.aevumprotocol/aevum
[![Anlyon Radar](https://radar.anlyon.com/badge/io.aevumprotocol/aevum.svg)](https://radar.anlyon.com/servers/io.aevumprotocol/aevum)

Source: MCP Registry. Synced Nov 17, 2026, 16:17 UTC.

Aevum: verified trading records MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Aevum: verified trading records MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 10 of which can change, send or delete something, and 3 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 Aevum: verified trading records MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Aevum: verified trading records MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: publish_agent_card, publish_call and check_payout_wallet.

What tools does the Aevum: verified trading records MCP server have?

14 tools: 3 irreversible, 7 write, 4 read. publish_agent_card, publish_call, check_payout_wallet, how_aevum_works, recheck_certificate, draft_call, register_agent, check_polymarket_wallet and 6 more.

Does the Aevum: verified trading records MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Aevum: verified trading records 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): publish_agent_card and publish_call.

Has the Aevum: verified trading records MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.