MCP.so
登录

Frontrun

@jongall45

关于 Frontrun

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.

基本信息

许可证

MIT

运行时

node

传输方式

stdio

发布者

jongall45

提交者

Jon Gall

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "frontrun": {
      "command": "npx",
      "args": [
        "frontrun-mcp-server",
        "--setup"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Frontrun?

Frontrun is an MCP server providing VC follow intelligence for AI agents. It monitors the X (Twitter) follow graphs of top investors, detecting new follows, convergence signals, and trending companies before they are publicly announced. It is designed for investors, analysts, and anyone tracking early-stage deal flow.

How to use Frontrun?

Set up via OAuth login (npx frontrun-mcp-server --login) or a manual API key from frontrun.vc. After authentication, configure your client using --setup for Claude Desktop or --setup-code for Claude Code. Then ask natural‑language questions such as “What are the trending companies this week?” or “Show me convergence signals.” Frontrun provides 33 tools—all callable automatically by the AI based on your query.

Key features of Frontrun

  • Monitors VC follow activity on X for early signals.
  • Detects convergence when multiple VCs follow the same entity.
  • Provides AI‑classified company profiles (sector, stage, founders).
  • Offers real‑time feed, trending scans, and thesis search.
  • Includes custom rules, tagging, and webhook support.
  • Accessible via MCP tools or equivalent REST API endpoints.

Use cases of Frontrun

  • Daily deal flow: scan trending companies and recent follows of tracked VCs.
  • Deep research: get comprehensive overviews of a startup, its founders, and funding.
  • Discovery: find early‑stage entities that multiple VCs are following but you haven’t tracked.
  • Portfolio monitoring: track specific VC accounts and their sector focus.
  • Custom intelligence: create rules to flag companies in defined niches (e.g., stablecoin neobanks).

FAQ from Frontrun

What signal does Frontrun detect?

VCs typically follow a company 2–8 weeks before a funding announcement. Convergence—multiple VCs independently following the same account—is the strongest signal.

How do I set up Frontrun?

You can use OAuth login (npx frontrun-mcp-server --login) which opens a browser and saves credentials locally, or obtain a manual API key (starts with sig_) from your frontrun.vc settings. Then configure your client with the provided --setup or --setup-code commands.

How is Frontrun priced?

Each query costs a certain number of credits (e.g., 4 credits for a preview, 60 for a company deep‑dive). Pro plans include 10,000 credits per month, and auto‑refill is available. Checking your balance and managing rules/tags is free.

Where does my data live?

Credentials are stored locally in ~/.frontrun/credentials.json. All API responses are computed intelligence—not raw data—synthesized from multiple sources.

What clients does Frontrun support?

Claude Desktop, Claude Code, Cursor, and any MCP‑compatible client. Configuration examples are provided for each.

评论

更多 MCP 服务器