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

Frontrun MCP Server

作者:jongall45版本 2.6.0i★ 1i在你的电脑上运行
注册名称io.github.jongall45/frontrun-mcp-server

安装

概览

作者提供的说明(英文原文)

Track what 1,000+ VCs follow on X to surface startups before their round. Signal for AI agents.

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
  • 你需要填写:FRONTRUN_API_KEY

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。

你需要

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": {
    "frontrun": {
      "command": "npx",
      "args": [
        "-y",
        "frontrun-mcp-server"
      ],
      "env": {
        "FRONTRUN_API_KEY": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add frontrun --env FRONTRUN_API_KEY=your-value -- npx -y frontrun-mcp-server

运行前请先填写空着的值。

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": {
    "frontrun": {
      "command": "npx",
      "args": [
        "-y",
        "frontrun-mcp-server"
      ],
      "env": {
        "FRONTRUN_API_KEY": "your-value"
      }
    }
  }
}

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": {
    "frontrun": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "frontrun-mcp-server"
      ],
      "env": {
        "FRONTRUN_API_KEY": "your-value"
      }
    }
  }
}

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。

需要你填写的值

  • FRONTRUN_API_KEY 机密 env
    Optional — the server runs OAuth device-flow setup if unset. API + MCP access is included with the Pro plan ($99/mo) at https://www.frontrun.vc.

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。

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

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11日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 jongall45 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于3个月前

  • … 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 19111 个服务器的 82%
  • 发布到注册中心的时间比此分类中其他 19111 个服务器的 16% 更新
  • 基础检查结果等于或优于此分类中其他 19111 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

Frontrun MCP Server 安全吗?

它在 2 项适用的基础检查中通过了 2 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?

你需要填写:FRONTRUN_API_KEY

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3个月前,最新版本(2.6.0)于4个月前进入注册中心。

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。

有什么可以替代它?

同一分类中有:World Monitor, Claude Flow, Tldraw

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:↓ 每周下载量i★ 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

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 102 tools.

作者:koala73广泛使用★ 9万6天前更新

在云端运行✓ worldmonitor.app

Claude Flow

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

作者:ruvnet广泛使用↓ 1.4万/周★ 8.1万14个月前更新

在你的电脑上运行

Tldraw

Draw and visually collaborate with your agents on tldraw's canvas.

作者:tldraw广泛使用★ 5.1万8个月前更新

在云端运行

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。

Frontrun MCP Server

VC follow intelligence for AI agents. Track what top investors follow on X — detect new follows, convergence signals, and trending companies before they're announced.

33 tools. Version 2.5.2.

Setup (1 minute)

Option A: OAuth login (recommended)

No API key needed. Log in with your frontrun.vc account:

# Step 1: Log in — opens browser, saves credentials locally

npx frontrun-mcp-server --login

Step 2: Auto-configure your client

npx frontrun-mcp-server --setup # Claude Desktop npx frontrun-mcp-server --setup-code # Claude Code (uses claude mcp add)

Credentials are saved to ~/.frontrun/credentials.json. Other commands:

npx frontrun-mcp-server --status   # Check auth status

npx frontrun-mcp-server --logout # Clear saved credentials

Option B: Hosted endpoint (no install)

The server is also hosted at https://www.frontrun.vc/mcp (streamable HTTP). Point any remote-capable MCP client at it with your API key:

claude mcp add --transport http frontrun https://www.frontrun.vc/mcp --header "Authorization: Bearer sig_your_key_here"
Option C: Manual API key

If you prefer to use an API key directly, go to frontrun.vc → Settings > API Keys and generate a key (starts with sig_).

Claude Code

claude mcp add frontrun -e FRONTRUN_API_KEY=sig_your_key_here --scope user -- npx frontrun-mcp-server

Or add to .mcp.json in any project:

{

"mcpServers": { "frontrun": { "command": "npx", "args": ["frontrun-mcp-server"], "env": { "FRONTRUN_API_KEY": "sig_your_key_here" } } } }

</details>

Claude Desktop

Add to your config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{

"mcpServers": { "frontrun": { "command": "npx", "args": ["frontrun-mcp-server"], "env": { "FRONTRUN_API_KEY": "sig_your_key_here" } } } }

</details>

Cursor

Add to .cursor/mcp.json in your project:

{

"mcpServers": { "frontrun": { "command": "npx", "args": ["frontrun-mcp-server"], "env": { "FRONTRUN_API_KEY": "sig_your_key_here" } } } }

</details>

Any MCP-compatible client

FRONTRUN_API_KEY=sig_your_key_here npx frontrun-mcp-server
Start asking questions

Open your AI tool and try:

"What's trending in my tracked accounts this week?"


What can I ask?

Here are real prompts that work out of the box. Just type them into Claude Code, Claude Desktop, or Cursor.

Daily deal flow
  • "What are the trending companies this week?"
  • "Show me what my tracked VCs followed in the last 48 hours"
  • "Any convergence signals? Who are multiple VCs following independently?"
Deep research
  • "Tell me everything about @hitdotone — who founded it, what they're building, and who's backing them"
  • "Who are the founders of @someproject and what's their background?"
  • "What funding has @tempofinance raised?"
Discovery
  • "Find me early-stage DeFi companies that my tracked VCs are following but I'm not tracking yet"
  • "What sectors are getting the most attention from VCs right now?"
  • "Search for stablecoin startups in the follow graph"
Portfolio monitoring
  • "Track @a16zcrypto and @paradigm"
  • "Show me a16zcrypto's recent follow activity and what sectors they're focused on"
  • "Find VCs with similar follow patterns to @multicoin"
Custom intelligence
  • "Create a rule to flag any stablecoin neobank companies"
  • "Tag @hitdotone as a portfolio candidate"
  • "Show me all entities matching my stablecoin rule from the last 7 days"

How it works

Frontrun monitors the X (Twitter) follow graphs of VCs and investors you choose to track. When a VC follows a new account, Frontrun detects it, classifies the entity (startup, protocol, founder, etc.), and makes it queryable through AI.

The signal: VCs typically follow companies 2-8 weeks before a funding announcement. Convergence — multiple VCs independently following the same account — is the strongest signal.

Receipts: @techdollarhq flagged at 13 followers, $3M pre-seed announced 123 days later · @orthogonal_sh flagged 184 days before its $4.3M round led by Pantera · @rialto_xyz flagged at 18 followers, 26 days before its Robinhood partner announcement.

What you're paying for: Every response is computed intelligence, not raw data. Sectors are classified by AI, convergence is detected algorithmically, and company profiles are synthesized from multiple sources.


Pricing

API + MCP access is included with the Pro plan ($99/mo) — it comes with 10,000 credits every month, and you can add more (or turn on auto-refill) at frontrun.vc/api/billing. Each query costs credits:

What you're doingCredits
Check your balance, list tracked accounts, manage rules/tagsFree
Preview an account, search, view sectors, pull a report4
New follows, enriched follows, feed, company signals16
Trending scan, VC activity24
Thesis search, webhook setup (then 8/delivery)40
Company deep-dive: overview, funding, convergence, resources, discover, similar VCs60
Founder intelligence100

A typical daily check-in (feed + convergence + a few company deep-dives) runs ~300 credits — an included month covers it more than 30x over. Agent-scale usage is what auto-refill is for.


All available tools

The agent has access to these tools automatically. You don't need to call them by name — just ask your question and the agent picks the right tool.

Tracking
ToolWhat it does
frontrun_statusYour balance, tracked count, usage stats
frontrun_list_trackedAll accounts you're monitoring
frontrun_trackStart monitoring an X account
frontrun_untrackStop monitoring an account
frontrun_previewPreview an account before tracking — signal score, sector hints, recommendation
Signals
ToolWhat it does
frontrun_new_followsNew follows detected across your tracked accounts
frontrun_snapshotCurrent follow list for a specific tracked account
frontrun_enriched_followsNew follows + AI classification + custom rules applied
frontrun_convergenceMultiple tracked accounts following the same entity
frontrun_trendingEntities ranked by follow velocity
frontrun_searchSearch discovered entities by sector, keyword, type
frontrun_thesis_searchSemantic search — describe a thesis in plain language, get matching companies
frontrun_feedReal-time activity feed across all tracked accounts
frontrun_sectorsSector breakdown of discovered entities
frontrun_discoverPersonalized recommendations — "accounts your VCs follow that you're not tracking"
frontrun_reportsGenerated intelligence reports for your tracked accounts
Company intelligence
ToolWhat it does
frontrun_companyCompany overview — what they do, sector, stage
frontrun_company_foundersFounder profiles, backgrounds, previous companies
frontrun_company_signalsSocial buzz, sentiment, notable engagements
frontrun_company_resourcesWebsite, GitHub, docs, community links
frontrun_company_fundingFunding rounds, investors, amounts
VC intelligence
ToolWhat it does
frontrun_vc_activityVC follow patterns — velocity, sector focus, recent follows
frontrun_vc_similarFind VCs with overlapping follow patterns
Classification
ToolWhat it does
frontrun_classifyRun AI classification on specific entities
frontrun_create_ruleCreate a custom classification rule
frontrun_list_rulesList your rules
frontrun_update_ruleUpdate a rule
frontrun_delete_ruleDelete a rule
frontrun_tagTag an entity with custom labels
frontrun_list_tagsList your tagged entities
Webhooks
ToolWhat it does
frontrun_list_webhooksList your registered webhooks
frontrun_create_webhookRegister a webhook for new_follows / convergence events
frontrun_delete_webhookDelete a webhook

REST API

Prefer HTTP? Every tool maps to a REST endpoint. Base URL: https://frontrun.vc/v1

# Set your key

export FR_KEY="sig_your_key_here"

Check your account

curl -sL -H "X-API-Key: $FR_KEY" "https://frontrun.vc/v1/status"

What's trending?

curl -sL -H "X-API-Key: $FR_KEY" "https://frontrun.vc/v1/trending?since=168h"

Convergence signals

curl -sL -H "X-API-Key: $FR_KEY" "https://frontrun.vc/v1/convergence?since=168h"

Full REST docs: frontrun.vc/docs/api


Support

License

MIT