Spark MCP

MCP serverSearch

Search and fetch AI agents, skills, prompts and MCP connectors from the Spark marketplace.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use Spark MCP

Install Spark MCP

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http spark-mcp 'https://spark.entire.vc/mcp/'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://spark.entire.vc/mcp/

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=spark-mcp&config=eyJ1cmwiOiJodHRwczovL3NwYXJrLmVudGlyZS52Yy9tY3AvIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://spark.entire.vc/mcp/

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add spark-mcp --url 'https://spark.entire.vc/mcp/'

    Run it once, then sign in with codex mcp login spark-mcp if the server asks for an account.

From the project's README

As published by entire-vc/evc-spark-mcp in README.md.

MCP server for Spark — your AI toolbox for real work. Search and discover agents, skills, prompts, bundles, and MCP connectors.


Quick Start

npx evc-spark-mcp

That's it. No API key needed.


Setup

Claude Code

claude mcp add spark -- npx -y evc-spark-mcp

Claude Desktop

Add to claude_desktop_config.json:

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

Cursor

Add to Cursor MCP settings:

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

OpenClaw

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

ChatGPT (via MCP bridge)

Any MCP-compatible client works — just point it at npx evc-spark-mcp.


Tools

ToolDescription
search_assetsSearch the Spark catalog by query, type, and domain
get_assetGet full details of an asset by slug
get_asset_contentGet raw prompt/skill content (best for prompts and skills)
list_popularList most popular assets by download count
list_categoriesList available domains and AI tags for filtering
get_api_key_infoCheck your API key status and daily usage
report_outcomeReport what happened when you applied fetched content: applied as is, applied with changes, broke, or not applicable

Resources

URI PatternDescription
spark://assets/{slug}Asset content as markdown
spark://catalog/{type}Asset list by type (agent, skill, prompt, etc.)

What's in the Catalog

Spark is a marketplace of AI workflow assets:

  • Agents — ready-to-use AI agent configurations
  • Skills — capabilities you can add to your agent (like this MCP server)
  • Prompts — tested prompt templates for specific tasks
  • Bundles — curated sets of tools that work together
  • MCP Connectors — integrations with external services

Find, share, and monetize AI tools — all in one place.


Configuration

Environment VariableDefaultDescription
SPARK_API_URLhttps://spark.entire.vc/api/v1Spark API base URL
SPARK_SITE_URLhttps://spark.entire.vcSpark website URL (for links)

Development

# Install dependencies
npm install

# Run in development mode
npm run dev

# Build
npm run build

# Test with MCP Inspector
npm run inspect

Part of the Entire VC Toolbox

ProductWhat it doesLink
Local SyncVault ↔ AI dev tools syncrepo
Team RelaySelf-hosted collaboration serverrepo
Team Relay PluginObsidian plugin for Team Relayrepo
OpenClaw SkillAI agent ↔ vault accessrepo
Spark MCP ← you are hereMCP server for Spark catalogthis repo

Community

License

MIT — Copyright (c) 2026 Entire VC

Advanced
Delivery
spark MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-github-entire-vc-spark
Source
github.com/entire-vc/evc-spark-mcp
Hosted endpoint
https://spark.entire.vc/mcp/