Skip to main content
Glama
LKbaba

Gemini MCP Server

by LKbaba
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
typeNoService account field (paste JSON approach). Set to 'service_account'.
auth_uriNoAuth URI (paste JSON approach).
client_idNoService account client ID (paste JSON approach).
token_uriNoToken URI (paste JSON approach).
project_idNoGCP project ID (paste JSON approach).
HTTPS_PROXYNoOptional proxy URL for users behind proxy/VPN.
private_keyNoPrivate key (paste JSON approach).
client_emailNoService account email (paste JSON approach).
GEMINI_API_KEYNoAPI key from Google AI Studio for AI Studio authentication mode.
private_key_idNoPrivate key ID (paste JSON approach).
universe_domainNoUniverse domain (paste JSON approach). Often 'googleapis.com'.
GOOGLE_CLOUD_PROJECTNoGCP project ID for explicit Vertex AI mode.
client_x509_cert_urlNoClient cert URL (paste JSON approach).
GOOGLE_CLOUD_LOCATIONNoRegion for Vertex AI (default: 'global').
GOOGLE_CREDENTIALS_JSONNoEntire service account JSON as a single string (explicit Vertex AI mode).
GOOGLE_GENAI_USE_VERTEXAINoSet to 'true' to enable explicit Vertex AI mode.
auth_provider_x509_cert_urlNoAuth provider cert URL (paste JSON approach).
GOOGLE_APPLICATION_CREDENTIALSNoFile path to service account JSON key (explicit Vertex AI mode).

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
gemini_multimodal_queryA

Query using images + text for multimodal understanding. Analyze designs, diagrams, screenshots, or any visual content with natural language questions.

gemini_analyze_contentA

Analyze code, documents, or data. Supports file path or direct content input. Provides summarization, code review, explanation, optimization, and debugging. Auto-detects content type and programming language.

TIP: This tool supports PARALLEL calls - analyze multiple files simultaneously for faster results.

gemini_analyze_codebaseA

Analyze entire codebase using 1M token context. Supports directory path, file paths, or file contents. Provides architecture overview, identifies patterns, security issues, performance bottlenecks, and dependency problems.

gemini_brainstormA

Generate creative ideas and solutions. Provides multiple ideas with pros/cons and feasibility assessment. Supports reading project context files to generate ideas that fit your project.

gemini_searchA

Search the web using Gemini's built-in Google Search grounding.

Features:

  • Returns up-to-date information with source citations

  • Supports thinkingLevel for reasoning depth control

  • Ideal for: current events, latest documentation, real-time data, fact-checking

Usage Tips:

  • Use thinkingLevel: 'low' for simple queries (faster response)

  • Use thinkingLevel: 'high' for complex analysis (deeper reasoning)

  • Use outputFormat: 'json' when you need structured data

  • Search results include source URLs in groundingMetadata

  • PARALLEL CALLS SUPPORTED: Search multiple queries simultaneously for faster results

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources