Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Tools

Functions exposed to the LLM to take actions

NameDescription
search_gemini_docs

Search the Gemini API documentation for relevant pages.

This tool searches through the Gemini API documentation index to find pages matching your query. It searches across page titles, categories, and keywords to find the most relevant documentation.

Args:

  • query (string): Search query to find relevant documentation (e.g., "function calling", "embeddings", "rate limits")

  • max_results (number): Maximum results to return, 1-20 (default: 10)

  • response_format ('markdown' | 'json'): Output format (default: 'markdown')

Returns: For JSON format: Structured data with schema: { "query": string, // The search query "total": number, // Number of results found "results": [ { "title": string, // Page title "path": string, // Documentation path (e.g., "function-calling") "url": string, // Full URL to the documentation page "category": string, // Category (e.g., "Core Capabilities") "matchedKeywords": [] // Keywords that matched the query } ] }

Examples:

  • "function calling" -> finds Function Calling documentation

  • "embeddings" -> finds Embeddings documentation

  • "authentication" or "api key" -> finds API Keys documentation

  • "rate limits" -> finds Rate Limits documentation

  • "vision" or "image" -> finds Image Understanding documentation

Use this tool first to find relevant documentation pages, then use fetch_gemini_doc to get the full content.

fetch_gemini_doc

Fetch and parse a specific Gemini API documentation page.

This tool fetches a documentation page from the Gemini API docs and extracts its content including title, sections, and code examples.

Args:

  • path (string): The documentation path (e.g., "function-calling", "embeddings"). Use empty string "" for the main overview page.

  • response_format ('markdown' | 'json'): Output format (default: 'markdown')

Returns: For JSON format: Structured data with schema: { "url": string, // Full URL of the page "title": string, // Page title "description": string, // Brief description "sections": [ { "level": number, // Heading level (1-6) "title": string, // Section title "content": string // Section content } ], "codeExamples": [ { "language": string, // Programming language "code": string // Code snippet } ], "fullText": string // Full text content (truncated if too long) }

Common paths:

  • "" (empty) - Main overview page

  • "quickstart" - Getting started guide

  • "function-calling" - Function calling / tool use

  • "embeddings" - Text embeddings

  • "structured-output" - JSON structured output

  • "text-generation" - Text generation basics

  • "image-understanding" - Vision / image analysis

  • "audio" - Audio understanding

  • "live" - Live API (real-time streaming)

  • "api-key" - API key setup

  • "models" - Available models

  • "pricing" - Pricing information

  • "rate-limits" - Rate limits and quotas

Use search_gemini_docs first to find the correct path if you're unsure.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LeomaiaJr/gemini-docs-skills'

If you have feedback or need assistance with the MCP directory API, please join our Discord server