← 返回 Skills 市场
575
总下载
0
收藏
3
当前安装
2
版本数
在 OpenClaw 中安装
/install openamc
功能描述
OpenAMC 本地 MCP 命令调用技能。通过标准化 CLI 接口，允许 AI Agent 主动向本地 MCP Server 发送查询指令以获取全球金融数据。覆盖 A股/港股（AKShare）、美股（yfinance）、宏观经济（FRED/IMF/EconDB）、美国国会（Congress）及衍生品、外汇、大宗...
安全使用建议
This skill appears to be an instruction-only connector that calls a local MCP server via the `mcp` CLI to fetch financial data — that is consistent with its description. However there are several mismatches in the package that you should resolve before installing:
- Confirm the source and provenance: the package has no homepage and the ownerId/version in _meta.json do not match the registry metadata. Ask the publisher to provide a canonical source (homepage, repository, signed release) and explain the owner/version discrepancy.
- Verify the `mcp` binary and MCP server: SKILL.md requires a locally installed `mcp` command and a server at http://127.0.0.1:8001. Ensure you trust the `mcp` binary (where it came from) and that the MCP server implementation is safe. The skill will call whatever functions that server exposes.
- Confirm permissions: _meta.json claims network and messaging permissions. Check whether the MCP server or `mcp` client will make outbound network calls beyond localhost or require credentials. If you do not want external network access, run the MCP server in an isolated environment and audit `mcp`'s behavior first.
- Test in a sandbox: before granting this to a production agent, run sample `mcp call openamc ...` commands manually on an isolated machine to observe what data is fetched and where traffic goes.
- Ask for missing details: request the publisher provide the `mcp` binary source, MCP server code or API spec, and a clear statement of required permissions. If these are not available or the publisher cannot explain the manifest mismatches, treat the skill as untrusted.
What would change this assessment: if the publisher supplies a verifiable repository or homepage, a signed release for the `mcp` binary, and an explicit manifest that consistently declares the required binary and permissions, this would move the assessment toward benign.
功能分析
Type: OpenClaw Skill
Name: openamc
Version: 1.0.1
The skill bundle is designed to query financial data via a local `mcp` command and a local OpenAMC MCP Server. All commands and instructions in `SKILL.md` are consistent with this stated purpose, focusing on data retrieval with structured JSON arguments. There is no evidence of prompt injection attempts against the AI agent, data exfiltration, malicious execution, persistence mechanisms, or obfuscation within the provided files. The `SKILL.md` explicitly disclaims 'automatic trading execution, continuous monitoring, or local system control logic', reinforcing its benign intent.
能力评估
Purpose & Capability
SKILL.md clearly describes a local MCP CLI-based connector that requires the `mcp` command and a local MCP server at http://127.0.0.1:8001. However the registry metadata at the top of the submission lists no required binaries or credentials while _meta.json includes an explicit handler (/usr/local/bin/mcp) and entrypoint pointing to the local MCP URL. The lack of a declared required-binaries entry in registry metadata is inconsistent with the skill's stated dependency on `mcp` and is disproportionate to its claimed purpose.
Instruction Scope
The SKILL.md instructions are narrowly scoped: they instruct the agent to run local `mcp call openamc ...` commands against a local MCP server to fetch financial data. That aligns with the stated purpose and does not instruct reading arbitrary host files or exfiltrating data. However the instructions give wide latitude to call many functions (193 tools) on the MCP server; the actual behavior depends on that server's implementation, which is not included.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so it does not itself write code to disk or download artifacts. That lowers install risk. The remaining risk depends on the external `mcp` binary and the MCP server implementation (both outside this package).
Credentials
The skill does not request environment variables or credentials in SKILL.md, and no secrets are required by the instruction text. This is proportionate to a local-data-query connector. However, the absence of declared env requirements contrasts with _meta.json's listed permissions (network, messaging), so verify that no external credentials will be requested by the local MCP server or `mcp` binary.
Persistence & Privilege
_meta.json lists 'permissions': ["network","messaging"] and includes an entrypoint and handler pointing to a local binary and URL. Although the skill itself does not request always:true or persistent config writes, the presence of network/messaging permissions in metadata (not visible in SKILL.md) is an elevated privilege claim and is inconsistent with the instruction-only surface. Also there are mismatches across manifest fields (ownerId and version differ from registry metadata), which raises provenance concerns about what the skill might be allowed to do if installed.
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 openamc - 安装完成后，直接呼叫该 Skill 的名称或使用
/openamc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
v1.0.1
- Clarified that the skill functions as a local MCP command connector for financial data queries, without trading or system control logic.
- Updated the description and introduction for greater accuracy and focus on CLI capabilities.
- No functional or command changes; all usage instructions and troubleshooting remain the same.
- Improved documentation to stress supported use cases and skill scope.
v1.0.0
OpenAMC 1.0.0 - 初始版本发布
- 上线全球金融情报终端，集成193个专业金融工具。
- 支持A股、港股、美股、外汇、宏观经济、政策、固定收益、大宗商品、加密货币等多市场多资产类别数据查询。
- 明确分门别类的命令行用法示例，并涵盖故障处理建议。
- 对接 AKShare、yfinance、FRED、IMF、EconDB、Congress 等主流数据源。
- 提供工具分类与自检指令，方便用户动态探索所有支持的功能及其用法。
- openamc 开放的资产管理机构
元数据
常见问题
openamc-mcp 是什么？
OpenAMC 本地 MCP 命令调用技能。通过标准化 CLI 接口，允许 AI Agent 主动向本地 MCP Server 发送查询指令以获取全球金融数据。覆盖 A股/港股（AKShare）、美股（yfinance）、宏观经济（FRED/IMF/EconDB）、美国国会（Congress）及衍生品、外汇、大宗... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 575 次。
如何安装 openamc-mcp？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openamc」即可一键安装，无需额外配置。
openamc-mcp 是免费的吗？
是的，openamc-mcp 完全免费（开源免费），可自由下载、安装和使用。
openamc-mcp 支持哪些平台？
openamc-mcp 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 openamc-mcp？
由 zhairen（@zhairen）开发并维护，当前版本 v1.0.1。
推荐 Skills