Google Spark MCP Skills Registry
Provides Google Spark (Gemini Spark) with on-demand access to agent skills, allowing it to dynamically query and apply skills such as UI/UX design, systematic debugging, code review, and anti-overengineering workflows.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Google Spark MCP Skills RegistryList the skills you have access to through MCP."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Google Spark MCP Skills Registry
A 24/7 Model Context Protocol (MCP) server providing on-demand agent skills to Google Spark (Gemini Spark).
Hosted on Render for always-on availability, allowing Spark to dynamically query and apply skills anytime—even when your personal computer is turned off.
Features
24/7 Cloud Availability: Hosted on Render as a lightweight Node.js web service.
On-Demand Dynamic Loading: When you tell Spark "use ui-ux-pro-max" or "audit with ponytail", Spark calls
get_skillto fetch that specific skill's guidelines in real time.63+ Portable Upstream Skills Included:
ui-ux-pro-max+ CKM Suite: 7 design & styling skills (79 design styles, 192 palettes, 22 stacks).obra/superpowers: 14 core agent workflows (TDD, systematic debugging, planning, worktrees).mattpocock/skills: 35+ architecture and code quality skills (code review, specs, tickets).DietrichGebert/ponytail: 6 anti-overengineering and debt-tracking skills.heygen-hyperframes: Video generation quickstart workflow.
Related MCP server: skillmds
MCP Tools Exposed to Google Spark
Tool | Parameters | Description |
|
| Lists available skills with descriptions and categories. |
|
| Fetches the full prompt instructions, rules, and reference files for a skill. |
|
| Searches skills across names, descriptions, and tags. |
Local Development & Testing
# 1. Install dependencies
npm install
# 2. Run in development mode
npm run dev
# 3. Build production bundle
npm run build
# 4. Start production server
npm startEndpoints
Web Status Page:
http://localhost:10000/Health Check:
http://localhost:10000/healthREST Skill Catalog:
http://localhost:10000/api/skillsMCP SSE Connection:
http://localhost:10000/sseMCP Message Handler:
http://localhost:10000/messages
Deploying to Render (1-Click Blueprint)
Push this repository to GitHub.
In Render Dashboard, click New + > Blueprint.
Select this repository. Render will automatically read
render.yamland configure:Type: Web Service
Build Command:
npm install && npm run buildStart Command:
npm startHealth Check:
/health
Once deployed, Render will provide a public HTTPS URL (e.g.
https://spark-skills-mcp.onrender.com).
Connecting to Google Spark
Open Gemini Web (
gemini.google.com).Go to Settings > Extensions / MCP Servers > Add MCP Server.
Enter your Render SSE URL:
https://your-spark-skills.onrender.com/sseSave and authorize.
Now, whenever you chat with Spark, you can say:
"List the skills you have access to through MCP."
"Build this feature. Use the systematic-debugging skill."
"Redesign this UI using ui-ux-pro-max."
This server cannot be deployed
Maintenance
Related MCP Connectors
Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.
Governed AI agent skills — one library, distributed to devs and exposed to remote agents over MCP.
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.
Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceServes Agent Skills over MCP using the SEP-2640 Skills Extension, enabling skills discovery, retrieval, and resource reading via MCP.-
- AlicenseNot gradedqualityAmaintenanceEnables MCP-capable agents to search, inspect, lint, and safely install Agent Skills from the skillmd registry mid-conversation.16 npm1MIT
- AlicenseNot gradedqualityBmaintenanceEnables centralized, versioned management and distribution of AI agent skills through a horizontally scalable MCP server, allowing agents to dynamically discover, search, and retrieve skills over HTTP/SSE.MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP clients to discover, search, and load agent skills from many sources, including other agents' skill directories, Claude Code plugin marketplaces, and remote git repositories, with no copying or syncing required.1,280 npm7MIT