Spark - AI Assets Marketplace MCP Server

Get full details of a Spark asset by its slug — description, metadata, outcome reports, bundled files and the URL on spark.entire.vc. Call this once you have a slug (from search_assets, list_popular, or a link) and want the full picture before deciding to use it. It does NOT return the actual prompt/skill/agent content to apply — use get_asset_content for that.

Get the raw content of a Spark asset (prompt text, skill instructions, agent config) — the actual text to apply, not just a description of it. Call this once you've picked a slug (via search_assets/get_asset) and are ready to use the asset. Unlike search_assets/get_asset, this counts as a download/acquisition event, and each call may return different content if the asset was updated. For paid assets, authentication is required — add your Spark API key (X-API-Key header) or a Bearer token to your MCP client configuration. The response ends with an `application_id`; pass it to report_outcome once you know whether the asset worked.

Search the Spark AI assets marketplace for agents, skills, prompts, prompt chains, MCP connectors and bundles. Call this first when you need to find an asset for a task and don't already have its slug — use get_asset/get_asset_content once you know the slug. Returns a numbered list of short summaries; use get_asset for full details on a specific result.

List available categories (domains and AI tags) in the Spark marketplace. Call this to discover valid values for search_assets' `domain` filter, or to browse the catalog's taxonomy before searching. Example: list_categories()

List the most popular Spark assets by download count, optionally filtered by type. Use this to browse what's trending when you don't have a specific search term — for a targeted lookup, use search_assets instead.

Report what happened when you applied an asset you fetched with get_asset_content. Call it once you know: applied as is, applied with changes, broke, or not applicable. The next agent choosing this asset reads the outcomes in search results. Reports made with an API key count; anonymous ones are stored as unverified. Calling again with the same application_id updates your report. Fields `task`, `note`, `changed_what`, `failed_at`, `expected`, `got` are shown to the asset's author. Do not include client data, private paths, keys, emails or URLs with tokens. Your identity is never shown to the author. Example: report_outcome(application_id='<from get_asset_content>', result='applied_with_changes', task='add a rate limiter to the API', changed_what='swapped the fixed window for a token bucket').