Same door for humans and AI. No gatekeeper.Register →
Explorer/MCP/centminmod/gemini-cli-mcp-server
REMOTE

Gemini CLI MCP Server

centminmod/gemini-cli-mcp-server

Bridges Google's Gemini CLI with MCP-compatible clients and integrates OpenRouter API for access to 400+ AI models. Provides 33 specialized tools enabling multi-AI workflows, collaborations, and debates between Claude, Gemini, and other LLMs.

↗centminmod/gemini-cli-mcp-serverExternal link; availability not verifiedRemote-capable
The Newcomer
Hasn't been around long. Nothing caught our attention, but there isn't much history to go on yet.
Time indexed (5mo)
0toolsRemote/ HTTP5moindexed
Checked Apr 18, 2026
The scanner shows
Not enough data to score this server yet.
First indexed Apr 18, 2026
Server Profile
⚙
Tools catalogued
0
No tools reported by this server.
☁
Hosting
Remote / HTTP
Runs on the internet. No access to your filesystem, SSH keys, or environment variables.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
—
No liveness checks recorded yet.
Publisher Verification
Not listed on the Official MCP Registry.
Source repository is available for review.
↗centminmod/gemini-cli-mcp-serverExternal link; availability not verified
Environment variables (49)
GEMINI_API_KEYstringOPTIONAL
Your Gemini API key for authentication
GEMINI_TIMEOUTstringOPTIONALdefault: 300
Command timeout in seconds (10-3600)
PROMETHEUS_PORTstringOPTIONALdefault: 8000
Prometheus metrics endpoint port
RETRY_MAX_DELAYstringOPTIONALdefault: 30.0
Maximum delay between retries in seconds (5.0-300.0)
GEMINI_LOG_LEVELstringOPTIONALdefault: INFO
Logging level (DEBUG, INFO, WARNING, ERROR)
Show all 49 environment variables
RETRY_BASE_DELAYstringOPTIONALdefault: 1.0
Base delay for exponential backoff in seconds (0.1-10.0)
ENABLE_MONITORINGstringOPTIONALdefault: false
Master control for all monitoring features
ENABLE_PROMETHEUSstringOPTIONALdefault: false
Enable Prometheus metrics collection
GEMINI_EVAL_LIMITstringOPTIONALdefault: 500000
gemini_eval_plan character limit
GEMINI_REDIS_HOSTstringOPTIONALdefault: localhost
Redis host for conversation storage
GEMINI_REDIS_PORTstringOPTIONALdefault: 6479
Redis port
ENABLE_STDIN_DEBUGstringOPTIONAL
Enable stdin debugging
OPENROUTER_API_KEYstringOPTIONAL
OpenRouter API key for 400+ models
RETRY_MAX_ATTEMPTSstringOPTIONALdefault: 3
Maximum retry attempts (1-10)
GEMINI_COMMAND_PATHstringOPTIONALdefault: gemini
Path to Gemini CLI executable
GEMINI_PROMPT_LIMITstringOPTIONALdefault: 100000
gemini_prompt character limit
GEMINI_REVIEW_LIMITstringOPTIONALdefault: 300000
gemini_review_code character limit
GEMINI_VERIFY_LIMITstringOPTIONALdefault: 800000
gemini_verify_solution character limit
JSONRPC_STRICT_MODEstringOPTIONALdefault: true
Enable strict JSON-RPC validation
ENABLE_HEALTH_CHECKSstringOPTIONALdefault: false
Enable health check system
ENABLE_OPENTELEMETRYstringOPTIONALdefault: false
Enable OpenTelemetry distributed tracing
GEMINI_OUTPUT_FORMATstringOPTIONALdefault: json
Response format (json, text)
GEMINI_SANDBOX_LIMITstringOPTIONALdefault: 200000
gemini_sandbox character limit
CLOUDFLARE_ACCOUNT_IDstringOPTIONAL
Cloudflare Account ID
CLOUDFLARE_GATEWAY_IDstringOPTIONAL
Cloudflare Gateway ID
GEMINI_ENABLE_FALLBACKstringOPTIONALdefault: true
Enable automatic model fallback
GEMINI_SUMMARIZE_LIMITstringOPTIONALdefault: 400000
gemini_summarize character limit
OPENTELEMETRY_ENDPOINTstringOPTIONALdefault: https://otel-collector:4317
OpenTelemetry endpoint
GEMINI_RATE_LIMIT_WINDOWstringOPTIONALdefault: 60
Time window in seconds
JSONRPC_MAX_REQUEST_SIZEstringOPTIONALdefault: 1048576
Max JSON-RPC request size in bytes (1MB default)
OPENROUTER_DEFAULT_MODELstringOPTIONALdefault: openai/gpt-4.1-nano
Default OpenRouter model
JSONRPC_MAX_NESTING_DEPTHstringOPTIONALdefault: 10
Max object/array nesting depth
GEMINI_RATE_LIMIT_REQUESTSstringOPTIONALdefault: 100
Requests per time window
OPENROUTER_MAX_FILE_TOKENSstringOPTIONALdefault: 50000
Per-file token limit for @filename
OPENTELEMETRY_SERVICE_NAMEstringOPTIONALdefault: gemini-cli-mcp-server
Service name for tracing
GEMINI_CONVERSATION_ENABLEDstringOPTIONALdefault: true
Enable conversation history
GEMINI_CONVERSATION_STORAGEstringOPTIONALdefault: redis
Storage backend (redis, memory, auto)
OPENROUTER_ENABLE_STREAMINGstringOPTIONALdefault: true
Enable streaming responses
OPENROUTER_MAX_TOTAL_TOKENSstringOPTIONALdefault: 150000
Total prompt token limit
GEMINI_SUMMARIZE_FILES_LIMITstringOPTIONALdefault: 800000
gemini_summarize_files character limit
CLOUDFLARE_AI_GATEWAY_ENABLEDstringOPTIONALdefault: false
Enable Cloudflare AI Gateway
CLOUDFLARE_AI_GATEWAY_TIMEOUTstringOPTIONALdefault: 300
Gateway timeout in seconds
OPENROUTER_COST_LIMIT_PER_DAYstringOPTIONALdefault: 10.0
Daily cost limit in USD
GEMINI_CONVERSATION_MAX_TOKENSstringOPTIONALdefault: 20000
Token history limit
GEMINI_SUBPROCESS_MAX_CPU_TIMEstringOPTIONALdefault: 300
Subprocess CPU time limit in seconds
GEMINI_SUBPROCESS_MAX_MEMORY_MBstringOPTIONALdefault: 512
Subprocess memory limit in MB
GEMINI_CONVERSATION_MAX_MESSAGESstringOPTIONALdefault: 10
Message history limit
CLOUDFLARE_AI_GATEWAY_MAX_RETRIESstringOPTIONALdefault: 3
Maximum retry attempts
GEMINI_CONVERSATION_EXPIRATION_HOURSstringOPTIONALdefault: 24
Auto-cleanup time in hours

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
Similar servers
Node.js Sandbox MCP Server
Enables running arbitrary JavaScript code in isolated Docker containers with on-the-fly npm dependency installation, supporting both ephemeral one-shot executions and persistent sandbox environments.
12306-MCP
12306 ticket purchase search server based on Model Context Protocol (MCP). It provides a simple API interface, allowing large models to search for 12306 ticket purchasing information through the interface.
Isolator MCP Server
A TypeScript server implementing the Model Context Protocol that provides secure code execution in isolated Docker containers, allowing LLM applications to safely run Python, Go, or JavaScript code snippets.
tacc-mcp-bio
Enables Claude Code to interact with a TACC or SLURM HPC cluster for bioinformatics pipelines, allowing job management, log reading, file browsing, remote script execution, and job submission through natural language.
io.github.XWeaponX7/rundida-mcp
Running tools for AI agents: 92 calculators, 46 guides, marathon data, pace and HR zones.
RooCode-RAG-Lookup
Enables semantic search across documents and code repositories using RAG (Retrieval-Augmented Generation) with vector embeddings. Automatically indexes PDF documents and performs relevance-scored lookups through ChromaDB and sentence transformers.
Indexed from Glama · Updates nightly