Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nirholas/three.ws --skill universal-crypto-mcp-guidegit clone --depth 1 https://github.com/nirholas/three.wsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nirholas/three.ws/universal-crypto-mcp-guide)<a href="https://agentmods.dev/skills/nirholas/three.ws/universal-crypto-mcp-guide"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/universal-crypto-mcp-guide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nirholas/three.ws/universal-crypto-mcp-guide"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/universal-crypto-mcp-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.01099 |
| Opus 5.5 | $0.00028 | $0.00440 |
| Sonnet 5.5 | $0.00014 | $0.00220 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
universal-crypto-mcp-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Crypto MCP Server Guide
The Universal Crypto MCP is a single MCP server that lets AI agents interact with any EVM blockchain through natural language. Instead of configuring separate servers for each chain, this one server handles everything.
Supported Chains
| Chain | Chain ID | RPC | Status |
|---|---|---|---|
| Ethereum | 1 | Public/Infura/Alchemy | ✅ |
| Arbitrum One | 42161 | Public | ✅ |
| Base | 8453 | Public | ✅ |
| Polygon | 137 | Public | ✅ |
| BSC | 56 | Public | ✅ |
| Optimism | 10 | Public | ✅ |
| Avalanche | 43114 | Public | ✅ |
| Sepolia Testnet | 11155111 | Public | ✅ |
Quick Start
npx @nirholas/universal-crypto-mcp
Claude Desktop Config
{
"mcpServers": {
"universal-crypto": {
"command": "npx",
"args": ["@nirholas/universal-crypto-mcp"]
}
}
}
Core Tools
Token Operations
| Tool | Description |
|---|---|
getBalance |
Get native/token balance on any chain |
getTokenInfo |
Token metadata (name, symbol, decimals, supply) |
transfer |
Transfer tokens between addresses |
approve |
Set token spending allowance |
DeFi Operations
| Tool | Description |
|---|---|
swap |
Execute token swap via DEX aggregator |
getSwapQuote |
Get swap quote without executing |
bridge |
Bridge tokens between chains |
stake |
Stake tokens in a protocol |
lend |
Supply tokens to lending protocol |
borrow |
Borrow against collateral |
Data & Analytics
| Tool | Description |
|---|---|
getPrice |
Current token price |
getGasPrice |
Gas price on target chain |
getTransactionHistory |
Address transaction history |
getContractInfo |
Smart contract details |
Plugin Architecture
The Universal Crypto MCP uses a plugin system for extensibility:
universal-crypto-mcp/
├── core/ # Base chain interactions
├── plugins/
│ ├── swap/ # DEX aggregation (1inch, 0x, Paraswap)
│ ├── bridge/ # Cross-chain (Across, Stargate, Hop)
│ ├── lending/ # Aave, Compound
│ ├── staking/ # Lido, Rocket Pool
│ └── custom/ # Add your own plugins
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 138 lines · 70 tokens per session scan A e98da94c2b16
universal-crypto-mcp-guide is a skill published in the GitHub repository nirholas/three.ws (246 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,099 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
evm
Read-only EVM client: wallets, tokens, gas across 8 chains.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, attach a workspace, defer capability…
mantis-threat-model
Synthesizes trust boundaries, attack surfaces, and attacker profiles into a living threat model. Use as Stage B of the Knowledge Base generation process, reading architecture and entity definitions from the KB. Don't use for analyzing source code or extracting raw learnings from JSONL files.
output-dev-workflow-function
Create workflow.ts files for Output SDK workflows. Use when defining workflow functions, orchestrating steps, or fixing workflow structure issues.
crypto-data
Use for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain; also when the user asks for on-chain SQL, wallet labels/net worth, social mindshare or crypto news, so they are told plainly what BlockRun…
rpc
Use when the user needs raw blockchain JSON-RPC access — contract reads (ethcall), native balances, blocks, transactions, logs, gas estimates, or any chain-native RPC method across 40 chains. One endpoint per chain via BlockRun's Tatum-backed gateway, $0.0030 per call, no node, no API key. Prefer blockrunprice /…