Server facts
evc-spark-mcp
Project
- Author
- entire-vc
- Repository
- github.com/entire-vc/evc-spark-mcp
- License
- Not specified
- Category
- Search & Web Data
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 4
- Last commit
- Data as of
Tags
- aggregator
- ai agents
- marketplace
- mcp
- search
Overview
Spark’s catalog groups agent configurations, skills, task prompts, curated bundles, and connectors for external services. evc-spark-mcp makes those assets searchable from an MCP client. With search_assets, users can narrow discovery by query, asset type, and domain; list_categories supplies the available domains and AI tags for filtering. For a different starting point, list_popular orders assets by download count. These tools support browsing the catalog or looking for an asset suited to a particular workflow.
After finding a candidate, users can call get_asset with its slug to retrieve details such as its description, content, files, and ratings. The separate get_asset_content tool retrieves raw material, including prompt text, skill instructions, or agent configuration, with particular relevance to prompts and skills containing inline content. Resources also expose individual assets as Markdown and catalog lists organized by type. The connection uses stdio and requires no API key. Setup examples cover Claude Code, Claude Desktop, Cursor, and OpenClaw, with ChatGPT access described through an MCP bridge.
evc-spark-mcp setup notes
- evc-spark-mcp records stdio only; confirm a network transport upstream before planning remote access.
- evc-spark-mcp has no recorded license; confirm reuse terms in its repository.