原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Signalfeed

作者:CloudCorpRecords版本 0.1.0i★ –i在你的电脑上运行
注册名称io.github.CloudCorpRecords/signalfeed

安装

概览

作者提供的说明(英文原文)

US filing-event streams in one schema: insider clusters, 13D/G, 13F, 8-K, Form D, FDA and more.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 注册中心没有列出需要填写的密钥。

你需要

  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "signalfeed": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/signalfeed",
        "mcp"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add signalfeed -- npx -y @reneturcios/signalfeed mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "signalfeed": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/signalfeed",
        "mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "signalfeed": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/signalfeed",
        "mcp"
      ]
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 CloudCorpRecords 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32564 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32564 个服务器的 92% 更新
  • 基础检查结果等于或优于此分类中其他 32564 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Signalfeed 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.1.0)于3天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js, Docker。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, Tools MCP

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

Tools MCP

作者:First-CH

Web production tools for AI agents: contrast, JP text, WebP, JSON-LD, slugs, dates and 40+ more

在你的电脑上运行今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

signalfeed

Twelve US filing-event streams, one schema, one key. signalfeed is a small client for the DataSignals Events API, which parses official filings into scored, decision-ready event records: insider buying clusters, planned insider sales (Form 144), activist stakes (13D/G), institutional holdings (13F), material events (8-K), private raises (Form D), FDA actions, biotech trial catalysts, NIH grants, federal contract awards, congressional trades and hiring signals. Every record links back to the filing it was parsed from, and where a record carries a score it also carries the terms that score was built from.

The feed is cursor-based: pass the cursor from one response back as since and you get exactly what arrived since — no duplicates, no gaps. Responses come back exactly as the API returned them: nothing is trimmed, renamed or summarised on the way through.

Configuration

  • DATASIGNALS_KEY — your API key. Required for the keyed tools; sent on those requests as Authorization: Bearer and never as a query parameter, so it does not end up in server logs or browser history. The keyless tools never send it.
  • DATASIGNALS_BASE_URL (optional) — API base URL. Defaults to https://datasignalslab.com.

A keyed tool called without a key fails locally with DATASIGNALS_KEY is not set, before any request is made. Two tools — list_event_types and feed_health — work without a key, so you can see the shape of the data and how fresh it is before you decide.

Tools

  • search_events — search filing events across all twelve streams. All filters are optional: event_type (one of the twelve stream ids), ticker, cik, min_score, plus since (the cursor from a previous response) and limit for paging. Only the filters you set are sent.
  • company_events — everything filed on one company, across all streams. company is a ticker or a CIK; since and limit page the result.
  • get_event — show everything on one event, by its event_id (for example insider_cluster:CAMP:2026-08-03).
  • list_event_types — which fields each stream carries, and whether its score can be recomputed. Works without a key.
  • feed_health — how current each stream is right now. Works without a key.
  • usage — how much of the monthly event allowance is used, and when it resets.
  • check_setup — whether the API key is configured and whether the feed answers. Always answers with a JSON object {key_configured, feed_reachable, detail}; the key value is never printed and no key is sent by the check itself.

Behaviour worth knowing:

  • A quota-exhausted feed does not throw an error mid-sync: it answers a 200 empty page with your cursor intact and a plain notice, and signalfeed passes it through like any other page.
  • The API scales to zero when idle. The first request after a quiet period may get a starting_up answer (with a Retry-After header) while it wakes, which can take about fifteen seconds; signalfeed returns that body as a normal result rather than an error, and the call is not counted against your allowance. Just call again.
  • Any other non-2xx reply fails with datasignals error: HTTP , and an unreachable API with datasignals unreachable.
Endpoint provenance

The vendor's Events API page pins the endpoints, the filter names, the cursor model and the twelve stream ids; the original MCP project's README pins the seven tools, both environment variables, the Bearer-header auth rule and the two keyless tools. The MCP-layer argument names follow the documented API names (a labelled reconstruction, since the MCP layer itself is unpublished):

  • GET /v1/events with only the set filters as query parameters (used by search_events).
  • GET /v1/companies/{ticker or cik}/events with since/limit when set (used by company_events).
  • GET /v1/events/{event_id} (used by get_event).
  • GET /v1/event-types (used by list_event_types, keyless).
  • GET /v1/health (used by feed_health, keyless, and by check_setup).
  • GET /v1/usage (used by usage).

event_id and company path segments are URL-encoded.

CLI

Each tool is a subcommand taking one JSON argument string:

npx @reneturcios/signalfeed search_events '{"event_type":"fda_action","min_score":70}'

npx @reneturcios/signalfeed company_events '{"company":"NVDA"}' npx @reneturcios/signalfeed get_event '{"event_id":"insider_cluster:CAMP:2026-08-03"}' npx @reneturcios/signalfeed list_event_types '{}' npx @reneturcios/signalfeed feed_health '{}' npx @reneturcios/signalfeed usage '{}' npx @reneturcios/signalfeed check_setup '{}' npx @reneturcios/signalfeed --version

Output is the tool's result text (the upstream body on success). Exit codes: 0 on success, 1 on a runtime error, 2 on a usage error.

MCP server

npx -y @reneturcios/signalfeed mcp

MCP client config:

{

"mcpServers": { "signalfeed": { "command": "npx", "args": ["-y", "@reneturcios/signalfeed", "mcp"], "env": { "DATASIGNALS_KEY": " " } } } }

Docker

docker run -i ghcr.io/cloudcorprecords/signalfeed

docker run --rm ghcr.io/cloudcorprecords/signalfeed feed_health '{}'

Development

npm install

npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (fake fetch only, no network) npm run dev # run the CLI from source

License

MIT — Copyright (c) 2026 Rene Turcios

问 PopNx