agentsbox
Discovers and executes MCP tools on-demand via agentsbox_* tools. Use when you need to find the right tool, when a user asks to use a tool you don’t have in context, or when troubleshooting MCP/tool availability.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 2.0k
- Forks
- 233
01 前言 Front Matter
- name
- agentsbox
- license
- MIT
- metadata
- { "author": "agentsbox", "version": "0.1" }
- description
- Discovers and executes MCP tools on-demand via agentsbox_* tools. Use when you need to find the right tool, when a user asks to use a tool you don’t have in context, or when troubleshooting MCP/tool availability.
02 资源文件 1
- 参考文档references/REFERENCE.md941 B
03 SKILL.md 正文
agentsbox
Minimize context bloat by using a small, stable tool surface:
agentsbox_search_bm25(natural language)agentsbox_search_regex(pattern search)agentsbox_execute(run discovered tool)agentsbox_status(health/status)agentsbox_perf(performance)agentsbox_test(tool verification)
Workflow
-
Search first
- If you don’t know the exact tool name:
agentsbox_search_bm25. - If you know server prefix / partial name:
agentsbox_search_regex.
- If you don’t know the exact tool name:
-
Inspect schema
- From search results, read
schemaand required fields.
- From search results, read
-
Execute
- Call
agentsbox_execute({ toolId, arguments }). toolIdformat:{serverName}_{toolName}.argumentsis a JSON string (or omit /{}when none required).
- Call
-
Troubleshoot
- If tool not found: widen search, verify server prefix, try BM25.
- If execution fails: run
agentsbox_status({})and include server diagnostics.
Examples
Search the web with tavily
- Search:
agentsbox_search_bm25({ "text": "search the web for information", "limit": 5 })
- Execute:
agentsbox_execute({
"toolId": "tavily_tavily_search",
"arguments": "{\"query\":\"latest AI news\",\"max_results\":5}"
})
Edge cases
- Empty or missing servers:
agentsbox_statuswill show zero configured servers. - Schema mismatch: prefer passing only required fields first.
- Server name/tool name ambiguity: use regex to list server tools:
"server_.*".
04 同仓库更多 Skills
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
neuropixels-analysis
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.