跳到正文
cccskills
免费在 GitHub 公开

fxmacrodata

Look up official macroeconomic releases, central-bank policy rates, release calendars and FX rates for 22 currencies through the FXMacroData MCP server. Use for questions about CPI, GDP, jobs data, rate decisions, bond yields or what data is due next, when the answer should come from the published number rather than news coverage. Remote server at https://mcp.fxmacrodata.com/mcp; USD works without a key.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md4.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

FXMacroData

Official-source macro and FX data via the FXMacroData MCP server: indicator histories, latest prints, scheduled releases, policy rates and FX rates for AUD, BRL, CAD, CHF, CNH, CNY, DKK, EUR, GBP, HUF, ILS, JPY, KRW, MYR, NGN, NOK, NZD, PEN, SEK, THB, TWD and USD.

Setup

The server is remote (Streamable HTTP), so there is nothing to install. USD data works without an API key: each release becomes readable 15 minutes after publication and covers the most recent 90 days, with a fair-use allowance of about 100 requests a day. Other currencies, FX rates, real-time releases and full history need a key from FXMacroData.

Without a key:

claude mcp add --transport http fxmacrodata https://mcp.fxmacrodata.com/mcp

With a key, set FXMACRODATA_API_KEY in your environment and send it as a bearer token:

claude mcp add --transport http fxmacrodata https://mcp.fxmacrodata.com/mcp --header "Authorization: Bearer ${FXMACRODATA_API_KEY}"

Or in .mcp.json:

{
  "mcpServers": {
    "fxmacrodata": {
      "type": "http",
      "url": "https://mcp.fxmacrodata.com/mcp",
      "headers": {
        "Authorization": "Bearer ${FXMACRODATA_API_KEY}"
      }
    }
  }
}

Full tool reference: MCP server docs.

Tools

  • data_catalogue - the indicator slugs available for a currency, with coverage dates. Call it first; slugs differ by currency
  • indicator_query - latest value and history for one indicator, each row with its release timestamp and the official source URL
  • latest_announcements - the most recent print of every indicator for a currency
  • release_calendar - scheduled releases, with confirmed times where the publisher has announced them
  • forex - FX rate history for a pair (key required)
  • rate_differentials and rate_curve - policy-rate gaps between two currencies and government yield curves
  • cot_data, commodities, market_sessions - CFTC positioning, metals and energy prices, and which FX sessions are open

The server also exposes multi-step research tools (macro_briefing_task, pair_intel_task and others) that this skill does not cover.

When to Use

  • "What did US CPI print this morning, and how does it compare with last month?"
  • "When is the next ECB decision?"
  • "Show the RBA cash rate over the last two years"
  • "What US data is due this week?"

Any question where the answer is a published statistic or a scheduled release.

How to Use

  1. Call data_catalogue for the currency to get the exact indicator slug (for example inflation, core_inflation, policy_rate, unemployment).
  2. Use indicator_query with that slug for the latest print and history, or release_calendar for what is coming up.
  3. Report the value with its period, release time and the publisher (for example "Bureau of Labor Statistics, via FXMacroData"), and link the source_url.
  4. Keep released values and forecasts apart. Released prints come from indicator_query; forecasts are a separate tool and are labelled with how they were produced.

User: "Has the Fed moved rates this year?"

Output: the policy-rate history for USD since January with each decision date, the current level, and the date of the next scheduled decision from the calendar.

Tips

  • A subscription_required result means the data exists but needs a key. Say so plainly and answer the USD equivalent if that helps; do not describe it as missing.
  • If a USD result reports a withheld release, the number has been published and will be readable within 15 minutes.
  • Keep calls narrow: one currency and indicator per call, and use limit on history.
  • If the server isn't configured, tell the user to add it with the command above.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36502026年10月19日 更新

Pull the ads a competitor is running right now on Meta (Facebook/Instagram) and Google, then extract the hooks, offers, CTAs and landing pages worth modelling. Use when writing ad copy, planning creative tests, choosing a landing page angle, or when the user asks "what is X advertising", "what ads does X run", "find competitor ad hooks". Reads live Ad Library and Ads Transparency data through the Tracetify MCP; falls back to a manual Ad Library walkthrough when the connector is absent.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36502026年10月19日 更新

Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36502026年10月19日 更新

Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36502026年10月19日 更新

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36502026年10月19日 更新

Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36502026年10月19日 更新

查看 davepoon 的全部技能

报告此技能的问题