← 返回 Skills 市场
Mcp Server Chart
作者
AI-Hub-Admin
· GitHub ↗
· v0.1.0
· MIT-0
113
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install mcp-server-chart
功能描述
Auto-generated skill for mcp-server-chart tools via OneKey Gateway.
安全使用建议
This skill appears to be a simple client wrapper that sends user-supplied chart data to the OneKey Gateway for chart generation — that behavior is coherent with its description. Before installing or running it, consider the following: (1) Any data you pass (including via --data-file) will be transmitted to the external OneKey service; do not send secrets or sensitive PII. (2) The scripts will use a built-in demo API key if you do not set DEEPNLP_ONEKEY_ROUTER_ACCESS, which may cause your data to be processed under a shared/demo account — set your own key or avoid using the skill if that is unacceptable. (3) The SKILL.md recommends installing an npm package even though the shipped code is Python; verify whether you actually need the npm dependency and the provenance of both the pip and npm packages (publisher, recent release, source repo) before installing. (4) If you need confidentiality, get documentation from the OneKey/DeepNLP provider about where data is sent/stored, or avoid sending sensitive data. If you want more assurance, request the upstream package repository URLs, provider privacy docs, or remove/ignore the npm step and only install the Python dependency after validating it.
功能分析
Type: OpenClaw Skill
Name: mcp-server-chart
Version: 0.1.0
The mcp-server-chart skill bundle provides a comprehensive set of tools for generating various charts, diagrams, and maps (e.g., area, bar, pie, district maps) via the DeepNLP OneKey Gateway. The Python scripts in the scripts/ directory are boilerplate wrappers that use the ai-agent-marketplace library to invoke remote API calls to deepnlp.org. The bundle requires an API key (DEEPNLP_ONEKEY_ROUTER_ACCESS) and follows its stated purpose without any evidence of malicious behavior, data exfiltration, or unauthorized execution.
能力评估
Purpose & Capability
The skill claims to provide chart-generation tools via the OneKey Gateway and the Python scripts do exactly that by instantiating OneKeyAgentRouter and invoking APIs like generate_area_chart. However, SKILL.md lists an npm dependency (@aiagenta2z/onekey-gateway) and an npm install step even though the provided runtime code is Python and imports the 'ai_agent_marketplace' package. The npm dependency appears unnecessary for the included Python scripts and is an inconsistency worth questioning.
Instruction Scope
Runtime instructions and the scripts are narrowly scoped: they accept a JSON payload (or a file) and call router.invoke with a fixed unique_id and the api_id for each chart type. The scripts do not attempt to read arbitrary system files or other environment variables beyond DEEPNLP_ONEKEY_ROUTER_ACCESS. The one notable runtime behavior is explicitly documented: if the DEEPNLP_ONEKEY_ROUTER_ACCESS env var is not set, the code falls back to a demo key ('BETA_TEST_KEY_MARCH_2026'), which means user data will still be transmitted to an external service.
Install Mechanism
The registry lists this as instruction-only (no formal install spec), but SKILL.md recommends installing packages via pip and npm. The Python package referenced (ai-agent-marketplace) aligns with the scripts. The npm package recommendation is inconsistent with the Python-only code. No downloads from arbitrary URLs or archive extraction are present in the files, so install risk is moderate and largely depends on the provenance of the suggested pip/npm packages.
Credentials
Only one env var is required (DEEPNLP_ONEKEY_ROUTER_ACCESS), which is appropriate for an API-client tool. However, the code's explicit default demo key means that if a user forgets or omits the env var, payloads will still be sent to the OneKey Gateway under a shared demo account. This increases the risk of inadvertent data exposure. The single declared env var is proportional to the purpose, but the fallback behavior is a privacy/security concern and should be called out.
Persistence & Privilege
The skill does not request permanent 'always' inclusion, does not modify other skills, and does not require system-level config paths or extra privileges. Autonomous invocation remains possible (platform default) but is not combined here with broad credential access or other high privileges.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install mcp-server-chart - 安装完成后,直接呼叫该 Skill 的名称或使用
/mcp-server-chart触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
Initial release of mcp-server-chart.
- Provides a unified interface to generate area, bar, boxplot, and column charts via OneKey Gateway.
- Supports custom data, grouping, stacking, styles, themes, and chart dimensions.
- Requires a OneKey Gateway API key, with a demo key fallback for testing.
- Installation instructions and parameter options included for both npm and Python environments.
元数据
常见问题
Mcp Server Chart 是什么?
Auto-generated skill for mcp-server-chart tools via OneKey Gateway. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 113 次。
如何安装 Mcp Server Chart?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mcp-server-chart」即可一键安装,无需额外配置。
Mcp Server Chart 是免费的吗?
是的,Mcp Server Chart 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Mcp Server Chart 支持哪些平台?
Mcp Server Chart 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Mcp Server Chart?
由 AI-Hub-Admin(@ai-hub-admin)开发并维护,当前版本 v0.1.0。
推荐 Skills