Skip to content

Automaton Token Safety MCP server

io.github.baianomarceloeduardo-jpg/automaton-token-safety-mcpbaianomarceloeduardo-jpgstreamable-httpv2.0.2Scanned

Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk.

20 tools: 1 do something that can't be undone, 18 change things and 1 only read.

Tools: 0 delete, 1 irreversible, 18 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • 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 Automaton Token Safety MCP server can do

The Automaton Token Safety MCP server is published by the GitHub account baianomarceloeduardo-jpg. It has 20 tools. It can do things that cannot be undone, such as sending, paying or publishing (simulate_base_transaction) and create or change data (18 tools: x402_conformance_check, token_scan, tx_simulate, approval_risk and 14 more), but cannot delete data. 1 tool only reads.

2 tools can send data out of your system (x402_conformance_check and simulate_base_transaction).

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.

Last scanned Nov 16, 2026, version 2.0.2.

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.

20 tools

Can't be undone 1Claude Code: ask
  • simulate_base_transactionFREE, runs locally against Base Mainnet RPC.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    FREE, runs locally against Base Mainnet RPC. Dry-run a transaction before sending it: eth_call + eth_estimateGas at the latest block. Predicts whether it will revert and decodes the reason (Error(string), Panic(uint256) codes, custom-error selector, or node rejection such as insufficient funds). Returns { ok, willRevert, revertReason, estimatedGas, returnData }.
Changes things 18Claude Code: ask
  • approval_riskPAID 0.01 USDC/call, or free trial (3/day/IP).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
    PAID 0.01 USDC/call, or free trial (3/day/IP). Read-only audit of the ERC-20 approvals an owner granted for a token: spender, allowance, contract vs EOA, verified flag, drainable amount and a drain-risk verdict. On 402, pay the accepts[] terms then retry with the payment tx hash.
  • attestCreate a SIGNED, hash-chained, append-only attestation (verifiable proof-of-existence) for a payload.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a SIGNED, hash-chained, append-only attestation (verifiable proof-of-existence) for a payload. PAID: 0.05 USDC/call, or free trial (3/day/IP). On 402, pay the accepts[] terms then retry with the payment tx hash.
  • attestation_pubkeyFREE.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
    FREE. Get the ECDSA P-256 public key (PEM) and keyId used to sign ledger entries.
  • hash_sha256PAID 0.001 USDC/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.
    Description, as the server wrote it
    PAID 0.001 USDC/call. SHA-256 hex of a string.
  • healthFREE.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
    FREE. Service liveness and version.
  • liquidity_riskPAID 0.01 USDC/call, or free trial (3/day/IP).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
    PAID 0.01 USDC/call, or free trial (3/day/IP). One-block liquidity audit of a Base token: Uniswap V3 / Aerodrome pools, the USD needed to move the price 1/2/5/10%, holder concentration, LP burn evidence and explicit coverage gaps. On 402, pay the accepts[] terms then retry with the payment tx hash.
  • merkle_provePAID 0.001 USDC/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.
    Description, as the server wrote it
    PAID 0.001 USDC/call. Generate a cryptographic Merkle inclusion proof for a list of items and target element.
  • merkle_verifyFREE.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
    FREE. Verify a cryptographic Merkle inclusion proof against a root.
  • oracle_basePAID 0.001 USDC/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.
    Description, as the server wrote it
    PAID 0.001 USDC/call. Get real-time Base L2 gas estimates and asset prices (ETH, USDC, cbBTC, AERO, VIRTUAL) with an ECDSA P-256 digital signature from the sovereign agent.
  • pricingFREE.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
    FREE. Full pricing terms, endpoints, and payment mechanics.
  • security_scanLEGACY NAME of token_scan — same route, same arguments, kept so clients written against this server keep working.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
    LEGACY NAME of token_scan — same route, same arguments, kept so clients written against this server keep working. PAID 0.001 USDC/call, or free trial (3/day/IP). Base token safety analysis: honeypot detection, mint traps, selfdestruct/delegatecall, proxy and tax risks from contract bytecode, with a risk score and signed verdict. On 402, pay the accepts[] terms then retry with the payment tx hash.
  • sentiment_analysisPAID 0.001 USDC/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.
    Description, as the server wrote it
    PAID 0.001 USDC/call. Web3 token risk, security checks, and sentiment scoring with signed verdict.
  • sentinel_latestPAID 0.001 USDC/call, or free trial (3/day/IP).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
    PAID 0.001 USDC/call, or free trial (3/day/IP). Newest liquidity pools created on Base (Uniswap v3/v4, Aerodrome) with a bytecode risk score per new token. Filters are optional. On 402, pay the accepts[] terms then retry with the payment tx hash.
  • token_scanPAID 0.001 USDC/call, or free trial (3/day/IP).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
    PAID 0.001 USDC/call, or free trial (3/day/IP). Bytecode security scan of a Base token contract: honeypot opcodes, mint/blacklist/pause/tax capabilities, a risk score and a verdict. Read-only — no transaction is sent. On 402, pay the accepts[] terms then retry with the payment tx hash. (Exposed as `security_scan` on older clients.)
  • tx_simulatePAID 0.01 USDC/call, or free trial (3/day/IP).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
    PAID 0.01 USDC/call, or free trial (3/day/IP). Read-only buy/sell simulation of a Base token through the Uniswap V2 WETH pool: returns reverts, the MEASURED transfer tax and a honeypot verdict. No transaction is sent. On 402, pay the accepts[] terms then retry with the payment tx hash. (Not the same tool as simulate_base_transaction, which dry-runs arbitrary calldata for free.)
  • uuidPAID 0.001 USDC/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.
    Description, as the server wrote it
    PAID 0.001 USDC/call. Generate a UUIDv4.
  • verify_attestationFREE.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
    FREE. Verify a ledger entry by index or by data hash: recomputes hash, checks ECDSA signature and chain link.
  • x402_conformance_checkFREE, runs locally.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    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
    FREE, runs locally. Lint any x402 paid endpoint for protocol conformance: HTTP 402 challenge, x402Version, accepts[] (exact scheme), Base network and addresses, EIP-712 domain, and rejection of malformed, forged, expired, underpaid and wrong-recipient EIP-3009 payments. Returns verdict, grade and per-check results.
Only reads 1Show 1 read-only tool
  • read_ledgerFREE.No findings

    Why it is in this group

    • The name "read_ledger" says "read": a word for reading.
    Description, as the server wrote it
    FREE. Read the attestation ledger (paginated).

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 out2
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:02 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
19
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 19 tools that change things (1 irreversible, 18 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.automaton-sovereign.workers.dev/mcp: tools/list returned 20 tools to an anonymous client, including simulate_base_transaction (irreversible), x402_conformance_check (write), token_scan (write), tx_simulate (write), approval_risk (write) and 14 more

    What this check looks for

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.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 2.0.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http automaton-token-safety https://api.automaton-sovereign.workers.dev/mcp
claude mcp add --transport http automaton-token-safety https://api.automaton-sovereign.workers.dev/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__automaton-token-safety__read_ledger"
    ],
    "ask": [
      "mcp__automaton-token-safety__x402_conformance_check",
      "mcp__automaton-token-safety__simulate_base_transaction",
      "mcp__automaton-token-safety__token_scan",
      "mcp__automaton-token-safety__tx_simulate",
      "mcp__automaton-token-safety__approval_risk",
      "mcp__automaton-token-safety__liquidity_risk",
      "mcp__automaton-token-safety__sentinel_latest",
      "mcp__automaton-token-safety__security_scan",
      "mcp__automaton-token-safety__attest",
      "mcp__automaton-token-safety__verify_attestation",
      "mcp__automaton-token-safety__attestation_pubkey",
      "mcp__automaton-token-safety__oracle_base",
      "mcp__automaton-token-safety__merkle_prove",
      "mcp__automaton-token-safety__merkle_verify",
      "mcp__automaton-token-safety__sentiment_analysis",
      "mcp__automaton-token-safety__hash_sha256",
      "mcp__automaton-token-safety__uuid",
      "mcp__automaton-token-safety__pricing",
      "mcp__automaton-token-safety__health"
    ],
    "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 automaton-token-safety. Review it before you use it.

Capability tags behind 2 rules
  • mcp__automaton-token-safety__x402_conformance_check outbound
  • mcp__automaton-token-safety__simulate_base_transaction 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.baianomarceloeduardo-jpg/automaton-token-safety-mcp/verify?hash=6e69fd057821184362fb697109d2083f753338137722a7b49076e3164fb76c01" | jq -e '.changed == false'

Pinned hash 6e69fd057821, from Nov 16, 2026, 10:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.baianomarceloeduardo-jpg/automaton-token-safety-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.baianomarceloeduardo-jpg/automaton-token-safety-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.baianomarceloeduardo-jpg/automaton-token-safety-mcp.svg)](https://radar.anlyon.com/servers/io.github.baianomarceloeduardo-jpg/automaton-token-safety-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:23 UTC.

Automaton Token Safety MCP server: questions and answers

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

Is the Automaton Token Safety MCP server safe?

No scan can promise that. What its definitions show: 20 tools, 19 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 Automaton Token Safety MCP server delete data?

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

Can the Automaton Token Safety MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: simulate_base_transaction.

What tools does the Automaton Token Safety MCP server have?

20 tools: 1 irreversible, 18 write, 1 read. simulate_base_transaction, x402_conformance_check, token_scan, tx_simulate, approval_risk, liquidity_risk, sentinel_latest, security_scan and 12 more.

Does the Automaton Token Safety MCP server need sign-in or OAuth?

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

Does the Automaton Token Safety 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): x402_conformance_check and simulate_base_transaction.

Has the Automaton Token Safety MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.