Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/diegosouzapw/awesome-omni-skill --skill 05-20-mcp-lessThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
| name | 05-20-mcp-less |
| description | Use MCP without installing |
You can call MCP servers directly from CLI/code with bunx — no Pi/Claude/Cursor connector setup required. Or write scripts/code for this flow.
Use @modelcontextprotocol/inspector in CLI mode.
# List tools
bunx --yes @modelcontextprotocol/inspector \
--cli https://your-mcp-server.example.com/mcp \
--transport http \
--method tools/list
# Call tool (no args)
bunx --yes @modelcontextprotocol/inspector \
--cli https://your-mcp-server.example.com/mcp \
--transport http \
--method tools/call \
--tool-name health_check
# Call tool (with args)
bunx --yes @modelcontextprotocol/inspector \
--cli https://your-mcp-server.example.com/mcp \
--transport http \
--method tools/call \
--tool-name my_tool \
--tool-arg 'query=hello world' \
--tool-arg 'limit=10'
bunx --yes @modelcontextprotocol/inspector \
--cli https://your-mcp-server.example.com/sse \
--transport sse \
--method tools/list
# Example: node server
bunx --yes @modelcontextprotocol/inspector \
--cli node ./dist/index.js \
--method tools/list
If a client only supports stdio servers, proxy a remote MCP via mcp-remote:
bunx --yes mcp-remote https://your-mcp-server.example.com/mcp --transport http-first
This runs a local stdio proxy connected to the remote MCP server.
For token-protected HTTP/SSE servers:
bunx --yes @modelcontextprotocol/inspector \
--cli https://your-mcp-server.example.com/mcp \
--transport http \
--header "Authorization: Bearer $TOKEN" \
--method tools/list
tools/listread_me, help, or describe)tools/call with minimal valid argsToken-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
AshAi extension guidelines for integrating AI capabilities with Ash Framework. Use when implementing vectorization/embeddings, exposing Ash actions as LLM tools, creating prompt-backed actions, or setting up MCP servers. Covers semantic search, LangChain integration, and structured outputs.
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.
Based on SOC occupation classification
