Hive Mcp Skill
v1.0.0Use Hive Intelligence MCP through UXC for broad crypto market, onchain, portfolio, and risk workflows with help-first discovery and convenience-layer guardra...
⭐ 0· 88·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the requested actions: the skill instructs the agent to use the Hive MCP endpoint via the uxc CLI wrapper and discover/invoke read-oriented endpoints. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
SKILL.md stays within the declared purpose: it links or uses hive-mcp-cli (uxc wrapper), discovers categories, inspects schemas, and invokes endpoints. Guardrails limit write operations and recommend narrow payloads. Note: the skill explicitly reuses the 'uxc' skill for auth/discovery — that means behavior and privileges can be expanded by whatever the uxc skill does, so review uxc if you trust this skill for sensitive workflows.
Install Mechanism
Instruction-only skill with no install spec. The only runtime dependency is a preinstalled 'uxc' CLI and network access to the official hiveintelligence.xyz endpoint. Provided validation script is local and only checks file contents; there is no remote download or archive extraction.
Credentials
The skill declares no required environment variables or credentials and includes a public, help-first flow that works without auth. The SKILL.md notes that higher-tier auth may appear later and that credentials must be bound explicitly if needed.
Persistence & Privilege
The skill is not always-enabled, does not request system-wide or other-skills' configuration access, and does not attempt to persist credentials or modify other skills. Autonomous invocation (model invocation) is enabled by default but not combined with other concerning flags.
Assessment
This skill is coherent and relatively low-risk, but consider the following before installing: (1) It makes network requests to https://hiveintelligence.xyz/mcp — verify you trust that endpoint and its TLS certificate. (2) It delegates discovery/auth handling to the 'uxc' skill/CLI — review that tool/skill to ensure it doesn't use or request unrelated credentials. (3) Never paste private keys, secrets, or other sensitive credentials into the agent when using discovery/invoke commands. (4) If you need long-term or write-capable workflows, require explicit review and explicit credential binding before enabling those operations. (5) The included validate.sh is a harmless repository linter; it will not be executed automatically by the agent, but you can run it locally to check file consistency.Like a lobster shell, security has layers — review code before you run it.
latestvk973ayxag8k5tekgdde2xxkr4n837z28
License
MIT-0
Free to use, modify, and redistribute. No attribution required.