Gemini MCP Ultimate 2.0.3 MCP tools and protocol inventory

Tools 8

Tool	Category	Annotations	Risk
ask-geminimodel selection [-m], sandbox [-s], and changeMode:boolean for providing edits Input schema { "type": "object", "properties": { "prompt": { "type": "string", "minLength": 1, "description": "Analysis request. Use @ syntax to include files (e.g., '@largefile.js explain what this does') or ask general questions" }, "model": { "type": "string", "description": "Optional model to use (e.g., 'gemini-3-flash-preview'). If not specified, uses the default model (gemini-3-pro-preview)." }, "sandbox": { "type": "boolean", "default": false, "description": "Use sandbox mode (-s flag) to safely test code changes, execute scripts, or run potentially risky operations in an isolated environment" }, "changeMode": { "type": "boolean", "default": false, "description": "Enable structured change mode - formats prompts to prevent tool errors and returns structured edit suggestions that Claude can apply directly" }, "chunkIndex": { "type": [ "number", "string" ], "description": "Which chunk to return (1-based)" }, "chunkCacheKey": { "type": "string", "description": "Optional cache key for continuation" }, "session_id": { "type": [ "string", "number" ], "description": "Session ID or index to resume a previous conversation context (maps to --resume)" }, "approval_mode": { "type": "string", "enum": [ "default", "auto_edit", "yolo" ], "default": "yolo", "description": "Autonomy control: 'default' (ask), 'auto_edit' (allow edits), 'yolo' (allow all)" }, "include_directories": { "type": "array", "items": { "type": "string" }, "description": "Additional directories to include in the workspace context" }, "output_format": { "type": "string", "enum": [ "text", "json", "stream-json" ], "description": "Output format: 'text' (default), 'json', or 'stream-json'" }, "experimental_acp": { "type": "boolean", "description": "Enable experimental ACP (Agentic Coding Protocol) mode" }, "allowed_tools": { "type": "array", "items": { "type": "string" }, "description": "Specific tools to allow without confirmation (overrides approval_mode)" } }, "required": [ "prompt" ] }	—	— · —	—
brainstormGenerate novel ideas with dynamic context gathering. --> Creative frameworks (SCAMPER, Design Thinking, etc.), domain context integration, idea clustering, feasibility analysis, and iterative refinement. Input schema { "type": "object", "properties": { "prompt": { "type": "string", "minLength": 1, "description": "Primary brainstorming challenge or question to explore" }, "model": { "type": "string", "description": "Optional model to use (e.g., 'gemini-3-flash-preview'). If not specified, uses the default model (gemini-3-pro-preview)." }, "methodology": { "type": "string", "enum": [ "divergent", "convergent", "scamper", "design-thinking", "lateral", "auto" ], "default": "auto", "description": "Brainstorming framework: 'divergent' (generate many ideas), 'convergent' (refine existing), 'scamper' (systematic triggers), 'design-thinking' (human-centered), 'lateral' (unexpected connections), 'auto' (AI selects best)" }, "domain": { "type": "string", "description": "Domain context for specialized brainstorming (e.g., 'software', 'business', 'creative', 'research', 'product', 'marketing')" }, "constraints": { "type": "string", "description": "Known limitations, requirements, or boundaries (budget, time, technical, legal, etc.)" }, "existingContext": { "type": "string", "description": "Background information, previous attempts, or current state to build upon" }, "ideaCount": { "type": "integer", "exclusiveMinimum": 0, "maximum": 100, "default": 12, "description": "Target number of ideas to generate (default: 12, max: 100)" }, "includeAnalysis": { "type": "boolean", "default": true, "description": "Include feasibility, impact, and implementation analysis for generated ideas" } }, "required": [ "prompt" ] }	—	— · —	—
fetch-chunkRetrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response. Input schema { "type": "object", "properties": { "cacheKey": { "type": "string", "description": "The cache key provided in the initial changeMode response" }, "chunkIndex": { "type": "number", "minimum": 1, "description": "Which chunk to retrieve (1-based index)" } }, "required": [ "cacheKey", "chunkIndex" ] }	—	— · —	—
Helpreceive help information Input schema { "type": "object", "properties": {}, "required": [] }	—	— · —	—
manage-extensionsManage Gemini CLI extensions: list, install, uninstall, update, enable, disable. Input schema { "type": "object", "properties": { "action": { "type": "string", "enum": [ "list", "install", "uninstall", "update", "enable", "disable", "validate" ], "description": "The action to perform on extensions." }, "target": { "type": "string", "description": "The name, path, or URL of the extension. Required for install, uninstall, enable, disable, update (single), and validate." }, "all": { "type": "boolean", "description": "Update all extensions. Only valid with 'update' action." }, "scope": { "type": "string", "description": "Scope for enable/disable (e.g. 'project' or 'global'). Defaults to project if omitted." } }, "required": [ "action" ] }	—	— · —	—
manage-sessionsManage conversation sessions: list active sessions or delete old ones. Input schema { "type": "object", "properties": { "action": { "type": "string", "enum": [ "list", "delete" ], "default": "list", "description": "Action to perform: 'list' active sessions or 'delete' a specific session" }, "session_id": { "type": "string", "description": "Session ID or index to delete (required for 'delete' action)" } }, "required": [] }	—	— · —	—
pingEcho Input schema { "type": "object", "properties": { "prompt": { "type": "string", "default": "", "description": "Message to echo back" } }, "required": [] }	—	— · —	—
timeout-testTest timeout prevention by running for a specified duration Input schema { "type": "object", "properties": { "duration": { "type": "number", "minimum": 10, "description": "Duration in milliseconds (minimum 10ms)" } }, "required": [ "duration" ] }	—	— · —	—

Prompts 6

ask-gemini

Execute 'gemini -p <prompt>' to get Gemini AI's response. Supports enhanced change mode for structured edit suggestions.

Metadata

{
  "prompt_key": "ask-gemini",
  "name": "ask-gemini",
  "description": "Execute 'gemini -p <prompt>' to get Gemini AI's response. Supports enhanced change mode for structured edit suggestions.",
  "arguments": [
    {
      "name": "prompt",
      "description": "Analysis request. Use @ syntax to include files (e.g., '@largefile.js explain what this does') or ask general questions",
      "required": true
    },
    {
      "name": "model",
      "description": "Optional model to use (e.g., 'gemini-3-flash-preview'). If not specified, uses the default model (gemini-3-pro-preview).",
      "required": false
    },
    {
      "name": "sandbox",
      "description": "Use sandbox mode (-s flag) to safely test code changes, execute scripts, or run potentially risky operations in an isolated environment",
      "required": false
    },
    {
      "name": "changeMode",
      "description": "Enable structured change mode - formats prompts to prevent tool errors and returns structured edit suggestions that Claude can apply directly",
      "required": false
    },
    {
      "name": "chunkIndex",
      "description": "Which chunk to return (1-based)",
      "required": false
    },
    {
      "name": "chunkCacheKey",
      "description": "Optional cache key for continuation",
      "required": false
    },
    {
      "name": "session_id",
      "description": "Session ID or index to resume a previous conversation context (maps to --resume)",
      "required": false
    },
    {
      "name": "approval_mode",
      "description": "Autonomy control: 'default' (ask), 'auto_edit' (allow edits), 'yolo' (allow all)",
      "required": false
    },
    {
      "name": "include_directories",
      "description": "Additional directories to include in the workspace context",
      "required": false
    },
    {
      "name": "output_format",
      "description": "Output format: 'text' (default), 'json', or 'stream-json'",
      "required": false
    },
    {
      "name": "experimental_acp",
      "description": "Enable experimental ACP (Agentic Coding Protocol) mode",
      "required": false
    },
    {
      "name": "allowed_tools",
      "description": "Specific tools to allow without confirmation (overrides approval_mode)",
      "required": false
    }
  ],
  "metadata_hash": "1d8e2167f14f09f1de66d8b3ecafadcb709453474f52f18c584299b660d67b00"
}

brainstorm

Generate structured brainstorming prompt with methodology-driven ideation, domain context integration, and analytical evaluation framework

Metadata

{
  "prompt_key": "brainstorm",
  "name": "brainstorm",
  "description": "Generate structured brainstorming prompt with methodology-driven ideation, domain context integration, and analytical evaluation framework",
  "arguments": [
    {
      "name": "prompt",
      "description": "Primary brainstorming challenge or question to explore",
      "required": true
    },
    {
      "name": "model",
      "description": "Optional model to use (e.g., 'gemini-3-flash-preview'). If not specified, uses the default model (gemini-3-pro-preview).",
      "required": false
    },
    {
      "name": "methodology",
      "description": "Brainstorming framework: 'divergent' (generate many ideas), 'convergent' (refine existing), 'scamper' (systematic triggers), 'design-thinking' (human-centered), 'lateral' (unexpected connections), 'auto' (AI selects best)",
      "required": false
    },
    {
      "name": "domain",
      "description": "Domain context for specialized brainstorming (e.g., 'software', 'business', 'creative', 'research', 'product', 'marketing')",
      "required": false
    },
    {
      "name": "constraints",
      "description": "Known limitations, requirements, or boundaries (budget, time, technical, legal, etc.)",
      "required": false
    },
    {
      "name": "existingContext",
      "description": "Background information, previous attempts, or current state to build upon",
      "required": false
    },
    {
      "name": "ideaCount",
      "description": "Target number of ideas to generate (default: 12, max: 100)",
      "required": false
    },
    {
      "name": "includeAnalysis",
      "description": "Include feasibility, impact, and implementation analysis for generated ideas",
      "required": false
    }
  ],
  "metadata_hash": "0374ba6d3cd6dbc6b64988b53cd0f295ab3099e1dcdb73544744d620c46e9bc7"
}

fetch-chunk

Fetch the next chunk of a response

Metadata

{
  "prompt_key": "fetch-chunk",
  "name": "fetch-chunk",
  "description": "Fetch the next chunk of a response",
  "arguments": [
    {
      "name": "prompt",
      "description": "fetch-chunk cacheKey=<key> chunkIndex=<number>",
      "required": true
    }
  ],
  "metadata_hash": "f8539a5c0d1608628f527906481aacb19b5871ebdc46a2ea18621306663b871e"
}

Help

receive help information

Metadata

{
  "prompt_key": "Help",
  "name": "Help",
  "description": "receive help information",
  "arguments": [],
  "metadata_hash": "c6f429def3cfc729b24d768211d4b0e53cdb3318e14c89c62f81df0033fa8ef0"
}

ping

Echo test message with structured response.

Metadata

{
  "prompt_key": "ping",
  "name": "ping",
  "description": "Echo test message with structured response.",
  "arguments": [
    {
      "name": "prompt",
      "description": "Message to echo back",
      "required": false
    }
  ],
  "metadata_hash": "1b03a660f5628e58f68653a78f5f85e754cf5b1bf80f4fa1c6c3e072d16240da"
}

timeout-test

Test the timeout prevention system by running a long operation

Metadata

{
  "prompt_key": "timeout-test",
  "name": "timeout-test",
  "description": "Test the timeout prevention system by running a long operation",
  "arguments": [
    {
      "name": "duration",
      "description": "Duration in milliseconds (minimum 10ms)",
      "required": true
    }
  ],
  "metadata_hash": "e287544c1e28af8183ce940fb3d1d31c676eed8572587f16cc449e04aa5ea802"
}

Gemini MCP Ultimate `2.0.3`

Observation

Tools 8

Resources 0

Resource templates 0

Prompts 6

Let’s talk about MCP security.