This server lets you discover, inspect, and use Spark AI marketplace assets.
Search assets by query, type, domain, and result limit.
Get full asset details by slug, including description, files, and ratings.
Fetch raw prompt, skill, or agent content by slug.
List popular assets by download count with optional type filtering.
List available categories, domains, and AI tags for filtering.
Access asset content and catalog lists via MCP resources like spark://assets/{slug} and spark://catalog/{type}.
Check API key status/daily usage and report outcomes after applying fetched content.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
MCP server for Spark — your AI toolbox for real work. Search and discover agents, skills, prompts, bundles, and MCP connectors.
npx evc-spark-mcpThat's it. No API key needed.
Related MCP server: SkillFlow MCP Server
claude mcp add spark -- npx -y evc-spark-mcpAdd to claude_desktop_config.json:
{
"mcpServers": {
"spark": {
"command": "npx",
"args": ["-y", "evc-spark-mcp"]
}
}
}This repository includes a Cursor plugin with a remote Spark MCP server and the
use-spark skill. No Node.js process or API key is needed for anonymous access.
To test a local install:
git clone https://github.com/entire-vc/evc-spark-mcp.git
mkdir -p ~/.cursor/plugins/local/spark
cp -R evc-spark-mcp/.cursor-plugin evc-spark-mcp/mcp.json \
evc-spark-mcp/server.json evc-spark-mcp/skills ~/.cursor/plugins/local/spark/Restart Cursor or run Developer: Reload Window, then open Customize and
confirm the use-spark skill and Spark MCP server. Enable the server if prompted;
its tools include search_assets, get_asset, get_asset_content, and
report_outcome. Try: “Find a Spark skill for reviewing Python code.”
Local plugin imports must be allowed by your team administrator. Copy the files:
Cursor skips symlinks whose target is outside ~/.cursor/plugins/local.
See Cursor's local plugin instructions.
For optional authenticated access, set SPARK_API_KEY in the environment used to
launch Cursor and restart it. mcp.json uses Cursor's ${env:SPARK_API_KEY}
interpolation for X-API-Key; leave it unset or empty for anonymous access. Never
put a key in the repository. Get a key from your Spark profile.
Plugin contents:
Path | Purpose |
| Cursor manifest with explicit relative component paths |
| Streamable HTTP connection to |
| Search, inspect, fetch, apply, and report outcomes |
| Remote server metadata; its version matches the plugin version |
The plugin follows the hosted server version (4.0.4), independently of the npm
stdio package version. When updating the hosted version, update server.json and the plugin manifest
together; npm test checks that they match.
{
"mcpServers": {
"spark": {
"command": "npx",
"args": ["-y", "evc-spark-mcp"]
}
}
}Any MCP-compatible client works — just point it at npx evc-spark-mcp.
Tool | Description |
| Search the Spark catalog by query, type, and domain |
| Get full details of an asset by slug |
| Get raw prompt/skill content (best for prompts and skills) |
| List most popular assets by download count |
| List available domains and AI tags for filtering |
| Check your API key status and daily usage |
| Report what happened when you applied fetched content: applied as is, applied with changes, broke, or not applicable |
URI Pattern | Description |
| Asset content as markdown |
| Asset list by type (agent, skill, prompt, etc.) |
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.
Environment Variable | Default | Description |
|
| Spark API base URL |
|
| Spark website URL (for links) |
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build
npm run build
# Test with MCP Inspector
npm run inspectProduct | What it does | Link |
Local Sync | Vault ↔ AI dev tools sync | |
Team Relay | Self-hosted collaboration server | |
Team Relay Sync | Obsidian plugin for Team Relay | |
OpenClaw Skill | AI agent ↔ vault access | |
Spark MCP ← you are here | MCP server for Spark catalog | this repo |
MIT — Copyright (c) 2026 Entire VC
Get full details of a Spark asset by its slug. Returns description, content, files, ratings, and more.
Inputs: slug (required).
Get the raw content of a Spark asset (prompt text, skill instructions, agent config). Best for prompts and skills that have inline content.
Inputs: slug (required).
List available categories (domains and AI tags) in the Spark marketplace. Useful for filtering searches.
Inputs: no named parameters.
List the most popular Spark assets by download count. Great for discovering top-rated AI tools.
Inputs: type, limit.
Search the Spark AI assets marketplace. Returns matching agents, skills, prompts, MCP connectors, and bundles.
Inputs: query (required), type, limit, domain.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose: retrieving full asset details, getting raw content, listing categories, listing popular assets, and searching. No ambiguity.
All tools follow a consistent verb_noun pattern in snake_case (e.g., get_asset, list_categories, search_assets), ensuring predictability.
Five tools is well-scoped for a marketplace discovery server, covering search, listing, and detailed retrieval without unnecessary complexity.
The tool set covers core marketplace operations (search, details, categories, popular items) but lacks a tool for user reviews or direct asset download, though get_asset includes ratings and likely download links.
Search and fetch curated AI agent skills, prompts and MCP servers.
Search & install 13,000+ AI agent skills from skills-hub.ai inside any MCP tool.
Find the right MCPs, tools and skills for any AI task - discovery over a 14k+ resource catalog.
AI agent registry — search, discover, register, and connect agents via MCP.
