Automaton Token Safety
NPM · @CELORODRIGUES/TOKEN-SAFETY-MCP · 2 COMPONENTS
Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk.
Available components
Last scanned (18 hours ago)
Scores higher than 62% of npm servers
Category Crypto and Web3
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 37 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability77
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1539 tokens (~102/item across 15 items; 15 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
- Stability observed for 28 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
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.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 −2
- Stability: pass → 0.90 functional
- 27 Oct 26 +1
- Stability: 0.97 → pass security
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
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 4 Nov 2026 · Analysed npm/@celorodrigues/token-safety-mcp@2.0.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
approval_risk ~107
Read-only audit of the ERC-20 approvals an owner granted for a token (PAID, 0.01 USDC): spender, allowance, contract vs EOA, verified flag, drainable amount and a drain-risk verdict.
| Name | Type | Req | Description |
|---|---|---|---|
| owner | string | yes | 0x-prefixed 40-hex address |
| spenders | array | – | Extra spenders to check beyond the log window |
| token | string | yes | 0x-prefixed 40-hex address |
No output schema declared.
No examples provided.
liquidity_risk ~97
One-block liquidity audit of a Base token (PAID, 0.01 USDC): Uniswap V3 / Aerodrome pools, USD needed to move the price 1/2/5/10%, concentration, LP burn evidence and explicit coverage gaps.
| Name | Type | Req | Description |
|---|---|---|---|
| pair | string | – | 0x-prefixed 40-hex address |
| token | string | yes | 0x-prefixed 40-hex address |
No output schema declared.
No examples provided.
security_scan ~132
LEGACY NAME of token_scan, kept for callers written against the previous edge MCP. Bytecode security scan of a Base token contract (PAID, 0.001 USDC): honeypot opcodes, mint/blacklist/pause/tax capabilities, risk score and verdict. The legacy `payment` argument is accepted and ignored — this server settles x402 on your behalf, so there is no tx hash to pass.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | 0x-prefixed 40-hex address |
| payment | string | – | Legacy argument, accepted and ignored: this server pays on your behalf. |
No output schema declared.
No examples provided.
sentinel_latest ~130
Newest liquidity pools created on Base (Uniswap v3/v4, Aerodrome) with a bytecode risk score per new token (PAID, 0.001 USDC). Filters are optional.
| Name | Type | Req | Description |
|---|---|---|---|
| dex | string | – | Restrict to one venue |
| limit | integer | – | Max pools to return (default 50) |
| maxRisk | number | – | Only pools whose risk score is at most this |
| minRisk | number | – | Only pools whose risk score is at least this |
| since | string | – | ISO-8601 timestamp; only pools detected after it |
No output schema declared.
No examples provided.
sentinel_stream ~200
Subscribe to the live Base pool channel (/v2/sentinel/stream, SSE, 0.01 USDC). Unlike the other five this is a CONTINUOUS channel, not a discrete RPC action: this tool opens it, collects events for a bounded window and returns what arrived, saying so plainly. Reading again is another call. The server applies the same risk and venue filters as sentinel_latest to the pools it pushes; the `hello` event echoes the filter in force, and the result reports it as `filter`.
| Name | Type | Req | Description |
|---|---|---|---|
| dex | string | – | Restrict to one venue |
| maxEvents | integer | – | Stop after this many events (default 50) |
| maxRisk | number | – | Only pools whose risk score is at most this |
| minRisk | number | – | Only pools whose risk score is at least this |
| windowSeconds | integer | – | How long to hold the channel open (default 15, max 60) |
No output schema declared.
No examples provided.
simulate_base_transaction ~183
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 }. No transaction is sent and nothing is paid.
| Name | Type | Req | Description |
|---|---|---|---|
| data | string | – | Calldata as 0x-hex (default 0x for a plain ETH transfer). |
| from | string | – | Optional sender address; needed for balance/allowance-dependent calls. |
| to | string | yes | Target contract or recipient address on Base (0x...). |
| value | string | – | ETH value in wei, decimal or 0x-hex (default 0). |
No output schema declared.
No examples provided.
token_scan ~77
Bytecode security scan of a Base token contract (PAID, 0.001 USDC). Reports honeypot opcodes, mint/blacklist/pause/tax capabilities, a risk score and a verdict. Read-only: no transaction is sent.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | 0x-prefixed 40-hex address |
No output schema declared.
No examples provided.
tx_simulate ~125
Read-only buy/sell simulation of a Base token through the Uniswap V2 WETH pool (PAID, 0.01 USDC). Returns reverts, the measured transfer tax and a honeypot verdict. No transaction is sent.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | string | yes | ETH for a buy, token units for a sell (positive decimal string) |
| side | string | yes | Trade direction being simulated |
| token | string | yes | 0x-prefixed 40-hex address |
| wallet | string | yes | 0x-prefixed 40-hex address |
No output schema declared.
No examples provided.
verify_payment ~94
Verify an on-chain ERC-20/USDC transfer on Base (free). Confirms the tx is real and confirmed, paid the right recipient, and met a minimum amount.
| Name | Type | Req | Description |
|---|---|---|---|
| minAmount | string | – | Minimum in token base units (USDC has 6 decimals; 1000 = 0.001). |
| to | string | yes | Expected recipient |
| tx | string | yes | 0x transaction hash |
No output schema declared.
No examples provided.
x402_conformance ~62
Audit ANY x402 service: fetches its 402 challenge and returns a pass/fail conformance verdict (scheme, network, chainId, asset, payTo, amount).
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Target service URL to audit (any https URL). |
No output schema declared.
No examples provided.
x402_health ~37
Check that the x402 Value API is live and read its advertised payment terms (network, chainId, asset, payTo, schemes).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
x402_index ~26
Read the live x402 service leaderboard (objectively scored by the conformance engine).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
x402_paid_uuid ~52
PAID call (0.001 USDC on Base) that returns a settled UUID, proving the whole x402 loop end to end. Settled by this server on your behalf when a payer is configured.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
x402_pricing ~33
Read per-route pricing for the Value API (USDC amounts per route, the six surfaces, the free trial).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
x402_submit ~43
Free self-submission: add your own x402 service to the public leaderboard. Returns the queued entry.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Your x402 service base URL. |
No output schema declared.
No examples provided.
How do I install the Automaton Token Safety MCP server?
Automaton Token Safety runs locally as an npm package, launched with npx -y @celorodrigues/token-safety-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @celorodrigues/token-safety-mcp
claude mcp add baianomarceloeduardo-jpg-automaton-token-safety- -- npx -y @celorodrigues/token-safety-mcp
What is the Automaton Token Safety MCP server?
Automaton Token Safety is an MCP server listed in the public MCP registry as io.github.baianomarceloeduardo-jpg/automaton-token-safety-m…. Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk. This page covers its npm package (@celorodrigues/token-safety-mcp).
Is the Automaton Token Safety MCP server safe to use?
Automaton Token Safety scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. 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 Automaton Token Safety MCP server expose?
Automaton Token Safety exposes 15 tools: token_scan, tx_simulate, approval_risk, liquidity_risk, sentinel_latest, and 10 more. Their descriptions and schemas cost roughly 1,398 tokens of context every time the server is loaded.
Is the Automaton Token Safety MCP server still maintained?
Automaton Token Safety is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Automaton Token Safety MCP server under?
Automaton Token Safety declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.