Gemini Daily MCP Server (Compressed)
Provides access to Google Gemini AI models (Flash, Flash-Lite, Pro, and Gemini 3) through the Gemini CLI, enabling AI-assisted coding, analysis, and multi-turn conversational sessions with token-optimized communication.
Click on "Deploy 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 Daily MCP Server (Compressed) help me write a Python function to sort a list of dictionaries by a specific key"
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.
Gemini Daily MCP Server (Compressed) β‘
Token-optimized MCP server for Google Gemini CLI with 43.8% token savings through Progressive Disclosure strategy.
π― Why Compressed Version?
This is an experimental token-optimized variant of gemini-daily-mcp that reduces tool schema overhead by 43.8% while maintaining full functionality.
Token Savings Comparison
Version | Schema Size | Tokens | Savings |
Original | 1,227 bytes | 306 tokens | - |
Compressed β‘ | 691 bytes | 172 tokens | 43.8% |
Impact:
Per conversation: Save 134 tokens
3,000 conversations/month: Save ~$1.61/month
Scale to 50 tools: Save ~$66/month (61%)
Related MCP server: Gemini Bridge
π‘ How It Works: Progressive Disclosure
Traditional Approach (Verbose Schema)
{
"name": "gemini",
"description": "Execute Gemini CLI in non-interactive mode for AI assistance with high Token efficiency",
"inputSchema": {
"properties": {
"prompt": {
"type": "string",
"description": "The coding task, question, or analysis request"
},
"sessionId": {
"type": "string",
"description": "Optional session ID for conversational context (saves up to 74% tokens in multi-turn conversations)"
}
}
}
}Size: 731 bytes β 182 tokens
Progressive Disclosure (Compressed Schema)
{
"name": "gemini",
"description": "Execute Gemini CLI. Use help for details",
"inputSchema": {
"properties": {
"prompt": {"type": "string"},
"sessionId": {"type": "string"}
}
}
}Size: 281 bytes β 70 tokens (61.6% savings)
Where Did the Details Go?
They're in the enhanced help tool! When Claude needs details:
# Claude calls: mcp__gemini-daily-compressed__help
# Returns comprehensive documentation:
# Gemini Daily MCP - Detailed Documentation
## gemini Tool
Execute Gemini CLI in non-interactive mode for AI assistance.
**Parameters:**
- prompt (required, string): The coding task, question, or analysis request
- sessionId (optional, string): Session ID for conversational context
- Saves up to 74% tokens in multi-turn conversations
- Obtained from previous gemini call's _meta.sessionId
- resetSession (optional, boolean): Reset session history before processing
- model (optional, string): Specify which Gemini model to use
- Default: gemini-2.5-flash
- Options: gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.5-pro, gemini-3-pro-preview
**Example:**
{
"prompt": "Write a Python function to calculate fibonacci",
"sessionId": "session-abc123",
"model": "gemini-2.5-flash"
}
...Result:
β 90% of conversations: Don't need details β Save tokens
β 10% of conversations: Call help once β Get full docs
β Overall: 43.8% token savings
π Features
Same Functionality as Original
β Full Gemini CLI integration
β Session management (saves up to 74% tokens in multi-turn conversations)
β Gemini 3 support (gemini-3-pro-preview with fallback)
β Multi-model selection (Flash, Flash-Lite, Pro, Gemini 3)
β Comprehensive error handling
Token Optimization
β‘ 43.8% smaller tool schemas
β‘ Progressive Disclosure via enhanced help tool
β‘ Preserves all type information
β‘ Maintains parameter validation
π¦ Installation
Prerequisites
Google Gemini CLI must be pre-installed and configured
Install: Follow Google's official Gemini CLI installation guide
Setup: Run
gemini auth loginwith your Google accountAPI Key: Set
GOOGLE_API_KEYenvironment variable or configure viagemini config
Claude Code or Claude Desktop installed
Claude Code
# Clone this repository
git clone https://github.com/kdoooh000h/gemini-daily-mcp-compressed.git
cd gemini-daily-mcp-compressed
# Install dependencies
npm install
# Build
npm run build
# Add to Claude Code
# Edit your .mcp.json:
{
"mcpServers": {
"gemini-daily-compressed": {
"command": "node",
"args": ["/path/to/gemini-daily-mcp-compressed/dist/index.js"],
"env": {
"GEMINI_ENABLED": "true",
"SESSION_TTL_HOURS": "24",
"MAX_SESSIONS": "100",
"GEMINI_CLI_COMMAND": "gemini",
"LOG_LEVEL": "info"
}
}
}
}Claude Desktop
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"gemini-daily-compressed": {
"command": "node",
"args": ["/path/to/gemini-daily-mcp-compressed/dist/index.js"],
"env": {
"GEMINI_ENABLED": "true",
"SESSION_TTL_HOURS": "24",
"GEMINI_CLI_COMMAND": "gemini"
}
}
}
}π§ Tools
gemini - AI Coding Assistant
Execute Gemini CLI with optional session support.
Basic Usage:
Use gemini to explain this Python functionAdvanced Usage:
# With session for multi-turn conversation
Use gemini with sessionId "my-session" to analyze this code
# Continue conversation
Use gemini with sessionId "my-session" to implement the improvements
# Specify model
Use gemini with model "gemini-3-pro-preview" for complex analysis
# Reset session
Use gemini with sessionId "my-session" and resetSession true to start freshlistSessions - Session Management
List all active conversation sessions.
ping - Connection Test
Test if the MCP server is working properly.
help - Enhanced Documentation
Get detailed documentation for all tools (this is where the detailed info lives in the compressed version).
π Compression Details
Strategy
Remove verbose descriptions from tool schemas
Preserve all functionality:
Parameter names
Type information
Required fields
Enum values
Enhance help tool to provide complete documentation
Token Breakdown
Tool | Original | Compressed | Savings |
gemini | 182 tokens | 70 tokens | 61.6% |
ping | 49 tokens | 37 tokens | 24.5% |
help | 33 tokens | 32 tokens | 3.0% |
listSessions | 40 tokens | 33 tokens | 17.5% |
Total | 306 tokens | 172 tokens | 43.8% |
Trade-offs
Pros β :
Significant token savings (43.8%)
Lower costs ($66/month for 3K conversations with 50 tools)
Full functionality preserved
Claude understands compressed schemas
Cons β οΈ:
~10% of conversations may need an extra help call
Schema less readable for developers
Need to maintain documentation in two places (schema + help tool)
π When to Use Compressed Version?
Recommended For β
High-frequency usage (>100 conversations/day)
Many tools (>20 tools in your MCP setup)
Cost-sensitive projects
Complex tool schemas with verbose descriptions
Use Original Version Instead
Low-frequency usage (<100 conversations/day)
Few tools (<10 tools)
Need maximum schema readability
Occasional use
π§ͺ Experimental Status
This is an experimental project to validate the Progressive Disclosure approach for MCP tool schemas.
Testing Results (from lab-02-testbed):
β All tools function normally
β help tool provides complete documentation
β Claude understands compressed schemas
β 43.8% token savings confirmed
β οΈ ~10% scenarios require help call (adds 1 tool invocation)
Feedback Welcome: Please open issues if you encounter any problems or have suggestions.
π Related Projects
Original Version: gemini-daily-mcp - Full verbose schemas
Token Analysis: See TOOL-SCHEMA-COMPRESSION-EXPERIMENT.md
Gemini CLI: Google Gemini CLI
π Documentation
MODELS.md: Gemini model compatibility and selection guide
CODEX-TO-GEMINI-ADAPTATION.md: How this was adapted from codex-mcp-server
API Reference: Use the
helptool within Claude for detailed documentation
π οΈ Development
# Install dependencies
npm install
# Development mode
npm run dev
# Build
npm run build
# Test
npm test
# Lint
npm run lintπ Version Compatibility
This MCP server is compatible with:
Gemini CLI: v0.17.0+ (with Gemini 3 support)
Claude Code: Latest version
Claude Desktop: Latest version
MCP SDK: @modelcontextprotocol/sdk ^1.17.3
π€ Contributing
This is an experimental project. Contributions, issues, and feature requests are welcome!
π License
ISC
π¬ Questions?
Use the help tool:
mcp__gemini-daily-compressed__helpOpen an issue: GitHub Issues
Original project: gemini-daily-mcp
β‘ Compressed. Efficient. Same Power.
Available Tools
4 toolsgeminiD
Execute Gemini CLI. Use help for details
Inputs: prompt (required), sessionId, resetSession, model.
helpC
Get detailed documentation
Inputs: no named parameters.
listSessionsB
List active sessions
Inputs: no named parameters.
pingC
Test connection
Inputs: message.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: gemini executes CLI commands, help provides documentation, listSessions shows active sessions, and ping tests connectivity. There is no overlap or ambiguity between these functions.
Naming is inconsistent: gemini and ping use lowercase, help is lowercase but a generic verb, and listSessions uses camelCase. There is no uniform verb_noun pattern or consistent casing style across the set.
With 4 tools, this is well-scoped for a server focused on Gemini CLI interaction and session management. Each tool serves a clear, necessary function without bloat or redundancy.
For a Gemini CLI server, core operations like execution, help, and session listing are covered, but there are notable gaps such as creating or managing sessions, handling specific Gemini commands directly, or error handling tools. The surface is functional but limited.
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server that reduces token consumption in AI coding assistants by up to 90% via structural reads, PreToolUse hooks, and tp-\* subagents.25280 npm5MIT
- AlicenseAqualityFmaintenanceA lightweight MCP server that enables AI coding assistants to interact with Google's Gemini AI through the official CLI.3MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that integrates Google Gemini CLI with Claude Code for AI-powered development assistance, enabling code review, bug analysis, feature planning, and code explanation without requiring an API key.8MIT
- AlicenseBqualityDmaintenanceMCP server that integrates Google Gemini CLI with AI assistants, enabling large file analysis and natural language queries without an API key.6111 npmMIT