ClawHub

Crypto.com MCP Skill

v1.0.0

Use Crypto.com MCP through UXC for exchange market data workflows with help-first discovery and read-only guardrails.

⭐ 0· 124·1 current·1 all-time
by@jolestar
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
The name/description describe read-only market-data access via Crypto.com MCP and the files/instructions match that purpose. The SKILL.md requires 'uxc' and a fixed MCP endpoint (mcp.crypto.com) which is appropriate. No unrelated environment variables, binaries, or config paths are requested. Note: the package source/homepage are not provided (source unknown), so provenance is unclear even though functionality is coherent.
✓
Instruction Scope
Runtime instructions are narrow and consistent: link a CLI via 'uxc', inspect help, and run read-only operations (ticker, book, candlestick, trades). The skill explicitly forbids trading/account writes and does not instruct reading unrelated files or environment variables. Network access is limited to the documented MCP endpoint and docs URL.
✓
Install Mechanism
There is no install spec (instruction-only skill). The included validation script is for developer/CI checks and not a runtime installer. No archives or external downloads are performed by the skill itself.
✓
Credentials
The skill declares no required environment variables, no credentials, and no config paths. That aligns with its stated read-only, public-market-data role. Be aware that authentication/credential handling may be delegated to the 'uxc' skill — review 'uxc' if you need to confirm how auth is managed.
✓
Persistence & Privilege
Flags show normal defaults (always: false, agent-invocable allowed). The skill does not request persistent system-wide changes or modify other skills' configs. Autonomous invocation is allowed by platform default; combine that with your local policy if you want to restrict autonomous calls.
Assessment
This skill appears coherent and limited to read-only market-data calls to Crypto.com's official MCP endpoint. Before installing: (1) confirm you trust 'uxc' because this skill delegates execution and possibly auth to it; (2) verify the MCP endpoint (https://mcp.crypto.com/market-data/mcp) and Crypto.com docs yourself; (3) note there is no published source/homepage for the skill — if provenance matters to you, request a canonical repository or vendor information from the publisher; (4) the included scripts reference 'rg' (ripgrep) for validation in CI only — not required at runtime; and (5) if you prefer to avoid autonomous network calls, restrict the skill to user-invocable or disable model invocation per your agent settings.

Like a lobster shell, security has layers — review code before you run it.

latestvk970gcz61mtcn681e6seyq3f0n8324a5

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments