広告掲載
MCP.so
ログイン
S

Spark MCP Server

@entire-vc

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

entire-vc

投稿者

Howard Eridani

Spark MCP Server について

Search and discover AI agents, skills, prompts, bundles and MCP connectors from a curated catalog of 4500+ assets.

#mcp#search#ai-agents#marketplace#aggregator

Spark MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "evc-spark-mcp": {
      "command": "npx",
      "args": [
        "evc-spark-mcp"
      ]
    }
  }
}

Spark MCP Server のツール

5

Search the Spark AI assets marketplace. Returns matching agents, skills, prompts, MCP connectors, and bundles.

Get full details of a Spark asset by its slug. Returns description, content, files, ratings, and more.

Get the raw content of a Spark asset (prompt text, skill instructions, agent config). Best for prompts and skills that have inline content.

List the most popular Spark assets by download count. Great for discovering top-rated AI tools.

List available categories (domains and AI tags) in the Spark marketplace. Useful for filtering searches.

概要

What is Spark MCP?

Spark MCP is a Model Context Protocol server for the Spark marketplace — a catalog of AI workflow assets such as agents, skills, prompts, bundles, and MCP connectors. It lets users search and discover these assets directly from any MCP‑compatible client without needing an API key.

How to use Spark MCP?

Run npx evc-spark-mcp to start the server. No API key or configuration is required. For Claude Code, Claude Desktop, Cursor, or OpenClaw, add the server to their MCP settings using the same npx command. Any MCP‑compatible client can connect by pointing to npx evc-spark-mcp.

Key features of Spark MCP

  • Search the Spark catalog by query, type, and domain
  • Get full details of an asset by its slug
  • Retrieve raw content of prompts and skills
  • List most popular assets by download count
  • Browse available domains and AI tags for filtering
  • Access asset content as markdown via resource URIs

Use cases of Spark MCP

  • Discover ready‑to‑use agent configurations for automation tasks
  • Find and add specific skills to enhance an AI agent’s capabilities
  • Retrieve tested prompt templates for common workflows
  • Explore curated bundles and MCP connectors for integrated tooling
  • Integrate the Spark marketplace into AI‑powered development tools

よくある質問

1

What exactly is Spark?

Spark is a marketplace of AI workflow assets including agents, skills, prompts, bundles, and MCP connectors — a place to find, share, and monetize AI tools.

2

Do I need an API key to use Spark MCP?

No. The server works out of the box with no API key required.

3

What tools does Spark MCP expose?

It exposes five tools: `search_assets`, `get_asset`, `get_asset_content`, `list_popular`, and `list_categories`.

4

How can I configure the server?

Set the environment variables `SPARK_API_URL` (default `https://spark.entire.vc/api/v1`) and `SPARK_SITE_URL` (default `https://spark.entire.vc`) to point to a different API or site.

5

Which MCP clients are supported?

Any MCP‑compatible client works, including Claude Code, Claude Desktop, Cursor, and OpenClaw.

コメント

「その他」の他のコンテンツ

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K
広告掲載