Gemini MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MCP_LICENSE | No | Your Gemini MCP license key for Pro/Enterprise tiers (optional for Free tier) | |
| OPENROUTER_API_KEY | Yes | Your OpenRouter API key (get free key from openrouter.ai) |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mcp__gemini__ai_chatC | AI conversation with model selection |
| mcp__gemini__code_analyzeC | Analyze code for quality and issues |
| mcp__gemini__create_project_tasksC | Create project tasks from requirements |
| mcp__gemini__system_statusC | Comprehensive system status showing all capabilities and performance metrics |
| mcp__gemini__generate_componentC | Generate UI components for React, Vue, Angular, Svelte |
| mcp__gemini__generate_apiC | Generate REST API endpoints with validation |
| mcp__gemini__refactor_suggestionsC | Get AI-powered refactoring suggestions |
| mcp__gemini__analyze_codebaseC | Comprehensive codebase analysis with AI insights |
| mcp__gemini__debug_analysisC | AI-powered debugging assistance |
| mcp__gemini__chat_plusC | Advanced collaborative AI chat with automatic model switching and context optimization |
| mcp__gemini__thinkdeep_enhancedC | Extended AI reasoning with step validation, logical consistency checking, and progress tracking |
| mcp__gemini__planner_proC | Interactive project planning with templates, dependency detection, and progress tracking |
| mcp__gemini__consensus_advancedC | Advanced multi-model consensus with weighted voting, confidence scoring, and conflict resolution |
| mcp__gemini__codereview_expertB | Multi-perspective code review with actionable fixes, risk scoring, and automated suggestions |
| mcp__gemini__debug_masterC | Advanced debugging with execution simulation, fix validation, and step-by-step analysis |
| mcp__gemini__analyze_intelligenceC | Deep code analysis with performance prediction, business impact assessment, and trend analysis |
| mcp__gemini__refactor_geniusC | Intelligent code refactoring with automated testing, rollback capabilities, and safety validation |
| mcp__gemini__precommit_guardianC | Advanced pre-commit validation with auto-fix suggestions and Git integration |
| mcp__gemini__secaudit_quantumC | Advanced security audit with vulnerability prediction, compliance checking, and quantum-readiness assessment |
| mcp__gemini__financial_impactC | ROI analysis and cost-benefit calculations for technical decisions with business impact quantification |
| mcp__gemini__performance_predictorC | AI-powered performance prediction and optimization recommendations with capacity planning |
| mcp__gemini__team_orchestratorC | Multi-developer collaboration with shared AI contexts and workflow coordination |
| mcp__gemini__quality_guardianC | Continuous quality monitoring and trend analysis with predictive quality metrics |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 23 tools
Multiple tools have significant overlap and unclear boundaries. For example, 'analyze_codebase', 'analyze_intelligence', 'code_analyze', and 'codereview_expert' all involve code analysis with overlapping purposes. Similarly, 'debug_analysis' and 'debug_master' both handle debugging, and 'refactor_genius' and 'refactor_suggestions' both focus on refactoring. This creates confusion about which tool to select for specific tasks, as descriptions don't clearly differentiate their scopes.
All tool names follow a consistent pattern: 'mcp__gemini__' prefix followed by descriptive snake_case phrases. The naming convention is uniform throughout, with no mixing of styles or deviations. This predictability makes it easy to identify tools as part of the same server and understand their general purpose from the naming structure.
With 23 tools, the count feels excessive for the server's purpose of AI-assisted development and analysis. Many tools appear to be specialized variants of core functions (e.g., multiple code analysis and debugging tools), suggesting fragmentation rather than a well-scoped set. This could overwhelm agents and lead to decision paralysis when selecting among similar options.
The tool set covers a broad range of AI-assisted development tasks, including code analysis, debugging, refactoring, project planning, security auditing, and collaboration. While there are some gaps (e.g., no explicit tools for code generation beyond APIs/components or version control operations), the surface is largely comprehensive for its domain, allowing agents to handle most workflows without dead ends.