gemini_list_voices

// WHEN AI AGENTS USE THIS TOOL

AI agents call gemini_list_voices to retrieve information from MCP Gemini without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

// WHY ENFORCE A POLICY ON GEMINI_LIST_VOICES

Even though gemini_list_voices only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

// RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

mcp-gemini.yaml

tools:
  gemini_list_voices:
    rules:
      - action: allow

See the full MCP Gemini policy for all 41 tools.

// DETAILS

Tool Name gemini_list_voices

Category Read

MCP Server MCP Gemini MCP Server

Risk Level Low

// MORE MCP GEMINI TOOLS

Destructive gemini_delete_cache Execute gemini_run_code Write gemini_continue_image_edit Write gemini_create_cache Write gemini_end_image_edit Write gemini_generate_image Write gemini_generate_image_with_input Write gemini_generate_video

View all 41 tools →

// WHAT CAN GO WRONG

Agents calling read-class tools like gemini_list_voices have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER READ TOOLS ACROSS MCP SERVERS

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

Open Library MCP Server get_author_info Open Library MCP Server get_author_photo Open Library MCP Server get_authors_by_name Open Library MCP Server get_book_by_id Open Library MCP Server get_book_by_title Open Library MCP Server get_book_cover

// RELATED READING

// FAQ

What does the gemini_list_voices tool do? +

List available text-to-speech voices. It is categorised as a Read tool in the MCP Gemini MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on gemini_list_voices? +

Add a rule in your Intercept YAML policy under the tools section for gemini_list_voices. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the MCP Gemini MCP server.

What risk level is gemini_list_voices? +

gemini_list_voices is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit gemini_list_voices? +

Yes. Add a rate_limit block to the gemini_list_voices rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block gemini_list_voices completely? +

Set action: deny in the Intercept policy for gemini_list_voices. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides gemini_list_voices? +

gemini_list_voices is provided by the MCP Gemini MCP server (mcp-gemini-crunchtools). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on MCP Gemini