io.github.CyberPunk11147/cyberwarex-defi-oracle
OCI · GHCR.IO/CYBERPUNK11147/CYBERWAREX-DEFI-ORACLE
Token safety: honeypot sim, contract powers, rug checks, watch alerts, plain card, paper test.
Available components
Last scanned (1 hour ago)
Scores higher than 51% of OCI 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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 12 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2614 tokens (~186/item across 14 items; 14 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 Management30
- Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 74% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 14 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
- Stability: unverified → 0.10 ▲ functional
- 14 Oct 26 +30
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Schema quality: excellent functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 74 functional
- 13 Oct 26 0
- Provenance: unverified → fail ▼ security
- 12 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
- 11 Oct 26 6
First indexed and scored.
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 23 Oct 2026 · Analysed oci/ghcr.io/cyberpunk11147/cyberwarex-defi-oracle@1.5.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
contract_risk ~229
Inspect what the team behind a token contract is able to do to holders, without running a trade simulation. Reports verified-source status, whether the contract is an upgradeable proxy and who its admin is, whether ownership is renounced, and which dangerous powers exist (mint, pause, blacklist, and mutable fees). Use it when you want the governance and rug-vector picture rather than the tradeability verdict. Returns JSON with each power as a boolean plus the resolved owner and admin addresses. Read-only. Paid per call in USDC on Base via x402.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The ERC-20 token contract address to evaluate: a 42-character hex string starting with 0x (for example 0x4200000000000000000000000000000000000006). This is the token you are about to buy, approve, or… |
| chain | string | – | Which chain the token lives on: 'base' for Base mainnet (the default) or 'bsc' for BNB Smart Chain. It must match the network the address is deployed on. |
No output schema declared.
No examples provided.
crowd_check_card ~155
The plain card for a token: who holds the supply, who can pull the pool, who holds powers over the token, and the largest sensible position, under 900 characters, with a verdict go, caution or no_go. A token too new or of unknown age is never a go. Base, Ethereum, Robinhood Chain, Solana. Not financial advice. Paid per call in USDC on Base via x402 ($0.10).
| Name | Type | Req | Description |
|---|---|---|---|
| chain | string | – | Chain the token lives on: base (default), ethereum, robinhood or solana. |
| token | string | yes | The token to check: a 0x contract address (Base, Ethereum, Robinhood Chain) or a Solana mint. |
No output schema declared.
No examples provided.
crowd_check_creator ~151
Who is behind this token? The creator wallet, the chain of wallets that funded it (followed up to 8 hops, so middle wallets do not hide the source), and that chain's record with us: how many earlier tokens it launched and how many rugged within a day. Flags serial launchers. Base, Ethereum, Robinhood Chain. Paid per call in USDC on Base via x402 ($0.02).
| Name | Type | Req | Description |
|---|---|---|---|
| chain | string | – | Chain the token lives on: base (default), ethereum, robinhood or solana. |
| token | string | yes | The token to check: a 0x contract address (Base, Ethereum, Robinhood Chain) or a Solana mint. |
No output schema declared.
No examples provided.
crowd_check_pool ~154
Can this token's liquidity be pulled? Who holds the pool share (burned, an ordinary wallet, a contract, a known fake locker), and for Uniswap v4 pools what the hook may do on every trade (take a cut, set any fee, block sells) and whether it is a launch platform's shared hook or the creator's own code. Paid per call in USDC on Base via x402 ($0.02).
| Name | Type | Req | Description |
|---|---|---|---|
| chain | string | – | Chain the token lives on: base (default), ethereum, robinhood or solana. |
| token | string | yes | The token to check: a 0x contract address (Base, Ethereum, Robinhood Chain) or a Solana mint. |
No output schema declared.
No examples provided.
crowd_check_verdict ~184
Should I touch this token? One go/no-go answer for trading bots and agents: verdict ok / caution / avoid, a 0-100 risk score, the top reasons, and key flags - can the liquidity be pulled, is the creator a serial launcher behind earlier rugs, what a Uniswap v4 hook may do, how much was bought in launch bundles. Works on Base, Ethereum, Robinhood Chain and Solana; fresh launches our hunt already checked answer instantly. Never charged while still computing. Paid per call in USDC on Base via x402 ($0.03).
| Name | Type | Req | Description |
|---|---|---|---|
| chain | string | – | Chain the token lives on: base (default), ethereum, robinhood or solana. |
| token | string | yes | The token to check: a 0x contract address (Base, Ethereum, Robinhood Chain) or a Solana mint. |
No output schema declared.
No examples provided.
honeypot_check ~233
Answer one focused question: can this token actually be sold after it is bought? Executes a real buy-then-sell round trip as a simulated transaction on Base or BSC. Use it when you only need the honeypot yes-or-no, not the full safety report. Returns JSON with: is_honeypot (boolean), buy_success (boolean), sell_success (boolean), and round_trip_loss_percent (the tax or slippage lost across the round trip). Read-only: no wallet needed. Paid per call in USDC on Base via x402.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The ERC-20 token contract address to evaluate: a 42-character hex string starting with 0x (for example 0x4200000000000000000000000000000000000006). This is the token you are about to buy, approve, or… |
| chain | string | – | Which chain the token lives on: 'base' for Base mainnet (the default) or 'bsc' for BNB Smart Chain. It must match the network the address is deployed on. |
No output schema declared.
No examples provided.
identity_quick ~169
The cheapest identity check: feed it a 0x address or an @handle and get back what kind of thing it is, a trust-or-credibility verdict, the top 3 red-flag signals, a one-line summary and the URL of the full endpoint to upgrade to. Uses cached full results when present, otherwise only the cheapest reads. Use it as a first pass before deciding whether a deeper wallet_identity or token_identity call is worth it. Returns JSON with: kind, trust_or_credibility, top_signals, summary, upgrade. Billable only when it answered. Paid per call in USDC on Base via x402 ($0.001).
| Name | Type | Req | Description |
|---|---|---|---|
| q | string | yes | A 0x address (wallet or token) or an X handle / x.com URL. |
No output schema declared.
No examples provided.
paper_backtest ~250
Paper test: what would have happened if you had followed a rule on every new token Crowd Check found? Replays the rule on our recorded outcomes with fees and price impact charged, and ALWAYS returns the same numbers for all tokens as a baseline, plus win rate with a 95% interval, average and median return, drawdown, crash rate and a plain verdict. Small samples are flagged. Past data only, not financial advice. Paid per call in USDC on Base via x402 ($0.05).
| Name | Type | Req | Description |
|---|---|---|---|
| bankroll | number | – | Starting bankroll in USD (100 to 10000000). |
| chain | string | – | – |
| exclude_kit | boolean | – | – |
| farm | string | – | – |
| horizon | integer | – | Hours to hold each token. |
| lp | string | – | – |
| max_liq | number | – | – |
| max_top10 | number | – | – |
| min_liq | number | – | – |
| preset | string | – | A ready-made rule to test. |
| since_days | integer | – | – |
| size_pct | number | – | Share of equity per trade, 0.0005 to 0.05 (default 0.005). |
No output schema declared.
No examples provided.
token_identity ~226
Find out who is behind a token, not just whether it is tradeable: our safety verdict (grade, honeypot), DexScreener market (liquidity, 24h volume, age, pair), the declared X account and website with checks that the website actually links the contract and the same X, and the creator wallet (Clanker admin or on-chain deployer) profiled like wallet_identity. Use it for due diligence on a new launch before buying, listing, or promoting it. Returns JSON with: name, symbol, safety, market, socials, creator, signals (IMPERSONATION, WASH_TRADING, DEAD_TOKEN, CREATOR_SERIAL_RUGGER, CREATOR_RUG_RING, NO_SOCIALS...), credibility (high/medium/low/unknown) and a summary. Base only. Not charged when nothing could be read. Paid per call in USDC on Base via x402 ($0.05).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The ERC-20 token contract address on Base, 42-char hex starting with 0x. |
No output schema declared.
No examples provided.
token_safety ~273
Decide whether an ERC-20 token is safe to trade before committing funds. Runs a live buy-then-sell simulation (Aerodrome and Uniswap V3) plus contract-power and ownership analysis and a GoPlus and honeypot.is cross-check, then returns a single verdict. Use it when an agent is about to swap into, approve, or accept a token it has not vetted. Returns JSON with: grade (A to F), risk_score (0-100), is_honeypot (boolean), tradeable (boolean), and a flags array where each flag carries on-chain evidence. Read-only: no wallet, key, or signature needed; a cold simulation can take a few seconds. Paid per call in USDC on Base via x402.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The ERC-20 token contract address to evaluate: a 42-character hex string starting with 0x (for example 0x4200000000000000000000000000000000000006). This is the token you are about to buy, approve, or… |
| chain | string | – | Which chain the token lives on: 'base' for Base mainnet (the default) or 'bsc' for BNB Smart Chain. It must match the network the address is deployed on. |
No output schema declared.
No examples provided.
wallet_identity ~231
Find out who is behind a wallet before trusting it: how old it is, how active, who first funded it, its ENS/Basename and the X account linked on it, every token it deployed and how many we proved were honeypots or scams (from 130k+ graded Base tokens), rug-ring funders and address-poisoning attempts. Use it when an agent is about to send funds to, accept a deal from, or rely on an unknown address. Returns JSON with: is_contract, first_seen, age_days, tx_count, funded_by, ens, linked_x, deployer, signals (stable ids with severity), trust (high/medium/low/unknown) and a one-line summary. Not charged when the wallet has no history. Paid per call in USDC on Base via x402 ($0.02).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The wallet (EOA or contract) address to profile, 42-char hex starting with 0x. |
| chain | string | – | Chain to read the wallet on: 'base' (default) or 'ethereum'. |
No output schema declared.
No examples provided.
watch_poll ~69
Ask a watch what changed since the last look. Returns plain-language alerts, or none if nothing moved. Not charged when market data is unavailable or the watch expired. Paid per call in USDC on Base via x402 ($0.01).
| Name | Type | Req | Description |
|---|---|---|---|
| ticket | string | yes | The ticket from watch_start. |
No output schema declared.
No examples provided.
watch_start ~129
Start a watch on a token and get a ticket. Poll it with watch_poll for plain alerts: pool liquidity down 30 percent, price down 50 percent, creator balance down 50 percent, measured from the best level since the watch began. Refused, with no charge, when the token has no market data. Paid per call in USDC on Base via x402 ($0.10).
| Name | Type | Req | Description |
|---|---|---|---|
| chain | string | – | – |
| hours | integer | – | How long to watch, 1 to 168 hours. |
| token | string | yes | Token contract address (or Solana mint). |
No output schema declared.
No examples provided.
x_identity ~161
Profile an X/Twitter account to judge whether a project or person is real: existence, account age, follower/following/tweet counts, verified status and type, website, and any wallet addresses in the bio. Use it when a token or counterparty points at an X account as proof of legitimacy. Returns JSON with: exists, created_at, age_days, followers, verified, website, bio_addresses, signals (e.g. NEW_ACCOUNT_BIG_FOLLOWING), trust (high/medium/low/unknown) and a summary. Paid per call in USDC on Base via x402 ($0.01).
| Name | Type | Req | Description |
|---|---|---|---|
| handle | string | yes | The X/Twitter handle to profile, with or without the leading @ (e.g. 'coinbase'). |
No output schema declared.
No examples provided.
How do I install the io.github.CyberPunk11147/cyberwarex-defi-oracle MCP server?
io.github.CyberPunk11147/cyberwarex-defi-oracle runs locally as a container image, launched with docker run --rm -i -e DSO_X_PAYMENT -e DSO_BASE_URL ghcr.io/cyberpunk11147/cyberwarex-defi-oracle:1.5.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/cyberpunk11147/cyberwarex-defi-oracle
claude mcp add cyberpunk11147-cyberwarex-defi-oracle -- docker run --rm -i -e DSO_X_PAYMENT -e DSO_BASE_URL ghcr.io/cyberpunk11147/cyberwarex-defi-oracle:1.5.0
This image reads DSO_X_PAYMENT and DSO_BASE_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.
What is the io.github.CyberPunk11147/cyberwarex-defi-oracle MCP server?
io.github.CyberPunk11147/cyberwarex-defi-oracle is an MCP server listed in the public MCP registry as io.github.CyberPunk11147/cyberwarex-defi-oracle. Token safety: honeypot sim, contract powers, rug checks, watch alerts, plain card, paper test. This page covers its container image (ghcr.io/cyberpunk11147/cyberwarex-defi-oracle).
Is the io.github.CyberPunk11147/cyberwarex-defi-oracle MCP server safe to use?
io.github.CyberPunk11147/cyberwarex-defi-oracle scores 40 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 io.github.CyberPunk11147/cyberwarex-defi-oracle MCP server expose?
io.github.CyberPunk11147/cyberwarex-defi-oracle exposes 14 tools: token_safety, honeypot_check, contract_risk, wallet_identity, x_identity, and 9 more. Their descriptions and schemas cost roughly 2,614 tokens of context every time the server is loaded.
Is the io.github.CyberPunk11147/cyberwarex-defi-oracle MCP server still maintained?
io.github.CyberPunk11147/cyberwarex-defi-oracle is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.