Gemini CLI Skills on Demand: Any Agent Skill via MCP

Gemini CLI skills without installing them

Short answer: add AnythingMCP to Gemini CLI's settings.json, install Agent Skills Finder on it, and ask Gemini for the task. It searches the public skills index, reads the best SKILL.md from GitHub and applies it.

Gemini CLI can load the skills and extensions you install for it. For the long tail of public skills, installing each one is more work than the task itself. Agent Skills Finder gives Gemini the whole catalogue on demand, and the same skills are available in every other client connected to your AnythingMCP server.

Set it up

Step 1: Add Agent Skills Finder on AnythingMCP

1. Create a workspace on AnythingMCP Cloud (7 days free) or use your self-hosted AnythingMCP.
2. Open Connectors, find Agent Skills Finder and click Install. It needs no credentials. On a new Cloud workspace it is also in the starter pack on the welcome screen.
3. For clients that use an API key (everything except claude.ai and ChatGPT), create one under MCP Servers → your server → API keys.

Step 2: Add AnythingMCP to Gemini CLI

Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

Save the file, restart gemini and run /mcp: anythingmcp should be listed with the Agent Skills Finder tools.

Step 3: Ask for a task

Start a new chat and describe what you need, for example "find a skill for writing release notes and use it on these commits". The agent calls the Agent Skills Finder tools on its own.

What happens when you ask

Say you ask Gemini CLI to write a README for this repository. Gemini CLI first calls skills_playbook, then skills_search with a few keywords, checks the best candidates' licence and activity with skills_repo_info, pins the version with skills_latest_commit and reads the instructions with skills_get. Then it does the task the way the skill describes and tells you which skill it used, with its link and licence. Nothing is installed and nothing stays loaded afterwards.

Prompts to try in Gemini CLI

• "Find a README-writing skill and write a README for this repository following it."
• "Search for a data-analysis skill and use it on sales.csv in this folder."
• "Look for a skill that writes shell scripts safely and rewrite deploy.sh with it."
• "Find a skill for writing a technical design doc and draft one for the feature in NOTES.md."

Good to know

• A skill is third-party text: Gemini CLI follows its method for your task, but it cannot change who the agent works for or skip your confirmation.
• The connector reads files and never runs scripts. Search is free for 50 queries a day, or 500 with a free SkillsMP key.
• To keep a skill for your team, ask Gemini CLI to save it as a workspace skill on AnythingMCP; an admin approves it once and it applies in every client.

How on-demand skills compare with installed ones, and every limit in detail: Agent Skills on demand.

FAQ

Do installed Gemini CLI skills and extensions still work? Yes. They load as before; the connector covers everything else.

Can Gemini run a skill's script? The connector reads files only. Gemini CLI can read the script; review it before running it.

Does it use my Gemini quota for searches? No. Searches go to SkillsMP (50 a day without a key, 500 with a free key); the model's tokens are only spent reading the skill it picks.

Can I use the same skills in Claude or Cursor? Yes. Every client connected to your AnythingMCP server uses the same connector and the same approved workspace skills.

Same skills in your other agents

• Agent Skills on demand: the overview
• Skills on demand in Claude
• Skills on demand in Claude Code
• Skills on demand in ChatGPT
• Skills on demand in OpenAI Codex
• Skills on demand in Cursor
• Skills on demand in GitHub Copilot
• Agent Skills Finder in the marketplace