MCP Gemini Server

Unclaimed

by bsmi021

This project provides a dedicated MCP (Model Context Protocol) server that wraps the @google/genai SDK. It exposes Google's Gemini model capabilities as standard MCP tools, allowing other LLMs (like Cline) or MCP-compatible systems to leverage Gemini's features as a backend workhorse.

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Tools (40)

allowedDomains

(array) - Specific domains to allow for this request

analysisType

(string enum) - Type of analysis to perform:

cachedContentName

(string) - Identifier for cached content to use with this request

comparison

Multi-URL content comparison

convertToMarkdown

(boolean) - Convert HTML to markdown (default: true)

defaultModel

(string) - Model to fall back to if routing fails. If not provided and routing fails, an error will be thrown.

displayName

(string) - Human-readable name for the cached content

extraction

Structured information extraction

fact-check

Credibility assessment

fetchOptions

(object) - Configuration for URL fetching

generationConfig

(object) - Controls generation parameters like temperature, topP, etc.

history

(array) - Initial conversation history

includeMetadata

(boolean) - Include URL metadata in context (default: true)

maxContentKb

(number) - Maximum content size per URL in KB (default: 100)

message

(string) - The text message to be routed to the most appropriate model

modelName

(string) - Name of the model to use

modelPreferences

(object) - Model selection preferences

models

(array) - Array of model names to consider for routing (e.g., ['gemini-1.5-flash', 'gemini-1.5-pro']). The first model in the list will be used for routing decisions.

negativePrompt

(string - features to avoid in the generated image)

numberOfImages

(number - 1-8, default: 1)

qa

Question-based content analysis

reasoningEffort

(string) - Simplified control: "none" (0 tokens), "low" (1K), "medium" (8K), "high" (24K)

resolution

(string enum: "512x512", "1024x1024", "1536x1536")

routingPrompt

(string) - Custom prompt to use for routing decisions. If not provided, a default routing prompt will be used.

safetySettings

(array) - Controls content filtering by harm category

seed

(number - integer value for reproducible generation)

sentiment

Emotional tone analysis

stylePreset

(string enum: "photographic", "digital-art", "cinematic", "anime", "3d-render", "oil-painting", "watercolor", "pixel-art", "sketch", "comic-book", "neon", "fantasy")

styleStrength

(number - strength of style preset, 0.0-1.0)

summary

Comprehensive content summarization

systemInstruction

(string or object) - System instruction to guide model behavior

thinkingBudget

(number) - Maximum tokens for reasoning (0-24576)

thinkingConfig

(object) - Controls model reasoning process

timeoutMs

(number) - Fetch timeout per URL in milliseconds (default: 10000)

toolConfig

(object) - Configures tool behavior like temperature and confidence thresholds

tools

(array) - Tool definitions including function declarations

ttl

(string - e.g., '3600s') - Time-to-live for the cached content

urlContext

(object) - Fetch and include web content from URLs

urls

(array) - URLs to fetch and include as context (max 20)

userAgent

(string) - Custom User-Agent header for URL requests