Provides tools to search and fetch Google's Gemini API documentation, allowing users to query topics like function calling or embeddings and retrieve structured content from specific documentation pages.
Click on "Install 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., "@Gemini Docs MCP Server find the documentation for function calling"
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.
An MCP (Model Context Protocol) server that provides tools to search and fetch Google's Gemini API documentation.
Search Documentation: Search through the Gemini API documentation index to find relevant pages
Fetch Documentation: Fetch and parse specific documentation pages with structured content extraction
Related MCP server: Anthropic Docs MCP Server
npm install
npm run buildnode dist/index.jsAdd to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"gemini-docs": {
"command": "node",
"args": ["/path/to/gemini-docs-mcp/dist/index.js"]
}
}
}search_gemini_docsSearch the Gemini API documentation for relevant pages.
Parameters:
query (string, required): Search query (e.g., "function calling", "embeddings")
max_results (number, optional): Maximum results to return (1-20, default: 10)
response_format (string, optional): Output format - "markdown" or "json" (default: "markdown")
Example:
{
"query": "function calling",
"max_results": 5,
"response_format": "json"
}fetch_gemini_docFetch and parse a specific Gemini API documentation page.
Parameters:
path (string, required): Documentation path (e.g., "embeddings", "function-calling"). Use empty string for the main overview page.
response_format (string, optional): Output format - "markdown" or "json" (default: "markdown")
Common paths:
"" - 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
live - Live API (real-time streaming)
api-key - API key setup
models - Available models
Example:
{
"path": "function-calling",
"response_format": "markdown"
}# Install dependencies
npm install
# Development mode with auto-reload
npm run dev
# Build
npm run build
# Run tests
npm run testFetch 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.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Documentation path (e.g., 'function-calling', 'embeddings', 'quickstart'). Use empty string for the main overview page. | |
| response_format | No | Output format: 'markdown' for human-readable or 'json' for machine-readable | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds valuable context beyond what annotations provide, including details about what content gets extracted (title, sections, code examples), output format options, and common usage paths. While annotations cover safety and idempotency, the description provides operational context that helps agents understand the tool's behavior in practice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and front-loaded with the core purpose, followed by organized sections for arguments, returns, common paths, and usage guidance. Every sentence serves a clear purpose with zero waste, making it efficient for both quick scanning and detailed reference.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and the absence of an output schema, the description provides comprehensive context including detailed return structure, common usage examples, and sibling tool guidance. The annotations cover safety aspects, and the description fills in operational details, making this complete for agent understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the baseline is 3, but the description adds significant value by providing a detailed return structure for JSON format and listing common path examples. This goes beyond the schema's basic parameter descriptions and helps users understand what to expect from the tool's output.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('fetch and parse') and resource ('Gemini API documentation page'), distinguishing it from the sibling tool search_gemini_docs. It explicitly mentions extracting content including title, sections, and code examples, providing a comprehensive overview of what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool versus alternatives, stating 'Use search_gemini_docs first to find the correct path if you're unsure.' It also lists common paths with examples, helping users understand appropriate contexts for usage and when to choose the sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query to find relevant documentation pages (e.g., 'function calling', 'embeddings', 'authentication') | |
| max_results | No | Maximum number of results to return (default: 10) | |
| response_format | No | Output format: 'markdown' for human-readable or 'json' for machine-readable | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is a read-only, non-destructive, idempotent operation with a closed world. The description adds valuable context about what gets searched (titles, categories, keywords) and provides concrete examples of search queries that work well, which helps the agent understand practical usage patterns beyond the safety profile covered by annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (description, args, returns, examples, usage guidance) and appropriately sized. While comprehensive, some information (like the detailed return format specification) might be slightly verbose given there's no output schema, but overall it's efficient and front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity, rich annotations, and 100% schema coverage, the description provides excellent completeness. It covers purpose, usage workflow with sibling tool, parameter examples, and return format details even without an output schema. The examples section adds practical guidance that helps the agent use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the input schema already documents all parameters thoroughly. The description adds minimal value beyond the schema, only providing example queries in the 'Examples' section. This meets the baseline of 3 since the schema does the heavy lifting for parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches the Gemini API documentation for relevant pages, specifying it searches across titles, categories, and keywords. It distinguishes from the sibling tool fetch_gemini_doc by indicating this tool finds pages while the sibling gets full content, making the purpose specific and differentiated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly provides usage guidance: 'Use this tool first to find relevant documentation pages, then use fetch_gemini_doc to get the full content.' This gives clear when-to-use instructions and names the alternative tool, helping the agent understand the workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0fetch_gemini_docsearch_gemini_docsThe two tools have clearly distinct purposes with no overlap: fetch_gemini_doc retrieves and parses specific documentation pages, while search_gemini_docs searches across the documentation index to find relevant pages. The descriptions explicitly guide users to use search first when unsure of the path, then fetch for detailed content, creating a logical workflow without confusion.
Both tools follow a perfect verb_noun pattern with consistent snake_case naming: fetch_gemini_doc and search_gemini_docs. The naming clearly indicates the action (fetch/search) and the target (gemini_doc/gemini_docs), making them predictable and easy to understand as a set.
With only 2 tools, this server feels thin for a documentation exploration domain. While the tools cover the core workflow of search-then-fetch, additional operations like listing available documentation categories or getting metadata about the documentation set would enhance completeness. The count is borderline minimal but functional.
For a documentation server, the surface covers the essential workflow: searching for relevant pages and fetching detailed content. The main gap is the lack of a tool to browse or list available documentation sections without searching, which could help agents discover content. However, the search tool with its comprehensive examples mitigates this gap reasonably well.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search and read the official MintMCP documentation, the enterprise MCP gateway.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Provides tools for searching Google Workspace documentation and much more.
Provides access to Google's public developer documentation.
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