Assess ERC-20 token safety and tradeability on Base or BSC via read-only, pay-per-call x402 tools.
Get an A–F token safety verdict with risk score, honeypot/tradeable booleans, and evidence-backed flags (token_safety).
Check whether a token can actually be sold after buying, including buy/sell success and round-trip loss (honeypot_check).
Inspect contract governance and rug risks: verified source, upgradeable proxy/admin, ownership renounced, and dangerous powers like mint, pause, blacklist, or mutable fees (contract_risk).
Specify chain as base or bsc; no wallet, key, or signature needed; paid per call in USDC on Base via x402.
Provides EVM chain data tools for Ethereum, including wallet, token, price, gas, transaction, and ENS lookups.
Provides EVM chain data tools for Optimism, including wallet, token, price, gas, and transaction lookups.
Provides EVM chain data tools for Polygon, including wallet, token, price, gas, and transaction lookups.
MCP (Model Context Protocol) servers for the CyberWareX suite — pay-per-call APIs built for AI agents. Every backing API is live, speaks x402 (HTTP 402 → pay USDC on Base → result), and needs no account and no API key: the first paid call is the entire onboarding.
Server | Tools | What it does | Price |
| Read any web page as LLM-ready markdown (JavaScript sites too), CSS extraction, screenshots, PDFs. Telegram search API: find public Telegram channels, groups and bots for a topic, look up any public @name with its latest posts, check if a channel is alive or inflated, no Telegram account. Public X, TikTok, Instagram, Facebook, LinkedIn profiles and company cards by domain | $0.001–$0.01 | |
| "Is this token safe to trade?" — live buy/sell simulation, contract powers, A–F grade with evidence (Base + BSC). New: Crypto Identity Graph — who is behind a wallet, token or X account (age, ENS, linked X, creator history, impersonation/rug signals from 130k+ graded tokens). 3 free calls/day with header | $0.001–$0.06 | |
| EVM data across Base, Ethereum, Arbitrum, Optimism, Polygon — no RPC keys, no node | $0.002–$0.004 | |
| Pre-sign safety for wallet/trading agents: simulate a tx before signing, decode EIP-712/personal_sign requests (drainer flags), sanctions + scam-ledger address screening, URL phishing score. 6 chains. 3 free calls/day per service | $0.002–$0.01 |
Retired: council (Agent Council) was shut down on 2026-11-04 and voice-stt (voice to text) on 2026-10-18; both are marked deprecated in the MCP registry. Their code stays in the repo for reference; the services no longer answer.
A runnable x402 example for trading agents: recipes/swap_guard.py. One call says go, caution or avoid before the swap ($0.03); after the buy a watch alerts on a pool drain or a price collapse ($0.10 to start, $0.01 a poll). First calls can be tried free with X-Free-Trial: 1 (3 a day per IP). Not financial advice.
Related MCP server: hyperd-mcp
pip install mcp requestsEach server is a single self-contained file speaking MCP over stdio:
python web-access/mcp_server.py{
"mcpServers": {
"cyberwarex-web": { "command": "python", "args": ["/path/to/cyberwarex-mcp/web-access/mcp_server.py"] },
"cyberwarex-oracle": { "command": "python", "args": ["/path/to/cyberwarex-mcp/defi-oracle/mcp_server.py"] },
"cyberwarex-chain": { "command": "python", "args": ["/path/to/cyberwarex-mcp/chain-data/mcp_server.py"] }
}
}These servers never hold keys and never pay. An unpaid tool call returns the x402
invoice (x402_payment_required: true with the full accepts block) so the calling
agent's x402 client can sign the gasless EIP-3009 USDC authorization and retry —
either through the agent's own payment stack, or by setting the *_X_PAYMENT env var
with a pre-signed payment header.
Machine-readable catalog of everything: https://cyberwarex.com/.well-known/x402 (LLM-readable summary at /llms.txt).
Server | Base URL override | Payment header | Timeout |
web-access |
|
|
|
defi-oracle |
|
|
|
chain-data |
|
|
|
Defaults point at the live public services — they work out of the box.
MIT — see LICENSE. Contact: x402@cyberwarex.com
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.
Inputs: address (required), chain.
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.
Inputs: address (required), chain.
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.
Inputs: address (required), chain.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
token_safety is the full-report umbrella and naturally overlaps with both honeypot_check and contract_risk, but the focused tools have clearly distinct single-purpose roles: sellability only vs. contract governance only. Descriptions make the separation actionable, though an agent might overuse token_safety when a lighter check would suffice.
All three tool names use lowercase snake_case and follow a consistent target_aspect pattern: token_safety, honeypot_check, contract_risk. There is no mixed casing or style drift, and each name clearly reflects its focused purpose.
Three tools is a well-scoped size for a token-security domain: one comprehensive vetting tool plus two dedicated focused checks. Each tool earns its place and there is no bloat or trivial filler.
The surface covers the core token-vetting workflow: full tradeability verdict, isolated honeypot detection, and contract-power/ownership risk. Minor gaps exist such as explicit liquidity-lock or approval-specific checks, but they are largely covered indirectly through the GoPlus and contract analysis layers.
30 pay-per-call APIs for AI agents: compliance, trade, safety, web, data. USDC on Base via x402.
Pay-per-call data APIs for AI agents. USDC on Base via x402. 33 tools, no signup.
Pay-per-call APIs built for AI agents: crypto market data, onchain checks, x402 tools, and the web and documents (web search, page fetch and extract, screenshots, PDF to text, an HTTP proxy, x402 marketplace search and pre-pay quotes). No API keys, no signup. Agents pay per call via x402 in USDC on Base.
31 pay-per-call APIs for AI agents: SEO, open data, video planning (EN/DE). USDC on Base via x402.
