MCP.so
Sign In

Frontrun

@jongall45

RepositoryHomepage

About 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.

#venture#investing#x#twitter

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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.

Frequently asked questions

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.

Comments

Basic information

License

MIT

Transports

stdio

Author

jongall45

Submitted by

Jon Gall

More MCP servers

TranscriptFetch MCP Server

TranscriptFetch

Model Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.

Reelier

Maxime Houle

Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.

Savi Tools

Savi Gurus AI Innovation Labs

Ask your AI assistant about your Savi Tools business: invoices, expenses, mileage, contacts, projects, taxes, and more. Read-only and OAuth-secured — your assistant sees only your own data at getsavitools.com, and you

patent-literature-search-mcp

patsnap

A professional tool for searching Patsnap’s global patent and literature databases using natural language, semantic, or keyword queries. It supports precise filtering and retrieves bibliographic data in Markdown format.

1

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

3