Gemini CLI MCP Server
by centminmod
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Your Gemini API key for authentication | |
| GEMINI_TIMEOUT | No | Command timeout in seconds (10-3600) | 300 |
| PROMETHEUS_PORT | No | Prometheus metrics endpoint port | 8000 |
| RETRY_MAX_DELAY | No | Maximum delay between retries in seconds (5.0-300.0) | 30.0 |
| GEMINI_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR) | INFO |
| RETRY_BASE_DELAY | No | Base delay for exponential backoff in seconds (0.1-10.0) | 1.0 |
| ENABLE_MONITORING | No | Master control for all monitoring features | false |
| ENABLE_PROMETHEUS | No | Enable Prometheus metrics collection | false |
| GEMINI_EVAL_LIMIT | No | gemini_eval_plan character limit | 500000 |
| GEMINI_REDIS_HOST | No | Redis host for conversation storage | localhost |
| GEMINI_REDIS_PORT | No | Redis port | 6479 |
| ENABLE_STDIN_DEBUG | No | Enable stdin debugging | |
| OPENROUTER_API_KEY | No | OpenRouter API key for 400+ models | |
| RETRY_MAX_ATTEMPTS | No | Maximum retry attempts (1-10) | 3 |
| GEMINI_COMMAND_PATH | No | Path to Gemini CLI executable | gemini |
| GEMINI_PROMPT_LIMIT | No | gemini_prompt character limit | 100000 |
| GEMINI_REVIEW_LIMIT | No | gemini_review_code character limit | 300000 |
| GEMINI_VERIFY_LIMIT | No | gemini_verify_solution character limit | 800000 |
| JSONRPC_STRICT_MODE | No | Enable strict JSON-RPC validation | true |
| ENABLE_HEALTH_CHECKS | No | Enable health check system | false |
| ENABLE_OPENTELEMETRY | No | Enable OpenTelemetry distributed tracing | false |
| GEMINI_OUTPUT_FORMAT | No | Response format (json, text) | json |
| GEMINI_SANDBOX_LIMIT | No | gemini_sandbox character limit | 200000 |
| CLOUDFLARE_ACCOUNT_ID | No | Cloudflare Account ID | |
| CLOUDFLARE_GATEWAY_ID | No | Cloudflare Gateway ID | |
| GEMINI_ENABLE_FALLBACK | No | Enable automatic model fallback | true |
| GEMINI_SUMMARIZE_LIMIT | No | gemini_summarize character limit | 400000 |
| OPENTELEMETRY_ENDPOINT | No | OpenTelemetry endpoint | https://otel-collector:4317 |
| GEMINI_RATE_LIMIT_WINDOW | No | Time window in seconds | 60 |
| JSONRPC_MAX_REQUEST_SIZE | No | Max JSON-RPC request size in bytes (1MB default) | 1048576 |
| OPENROUTER_DEFAULT_MODEL | No | Default OpenRouter model | openai/gpt-4.1-nano |
| JSONRPC_MAX_NESTING_DEPTH | No | Max object/array nesting depth | 10 |
| GEMINI_RATE_LIMIT_REQUESTS | No | Requests per time window | 100 |
| OPENROUTER_MAX_FILE_TOKENS | No | Per-file token limit for @filename | 50000 |
| OPENTELEMETRY_SERVICE_NAME | No | Service name for tracing | gemini-cli-mcp-server |
| GEMINI_CONVERSATION_ENABLED | No | Enable conversation history | true |
| GEMINI_CONVERSATION_STORAGE | No | Storage backend (redis, memory, auto) | redis |
| OPENROUTER_ENABLE_STREAMING | No | Enable streaming responses | true |
| OPENROUTER_MAX_TOTAL_TOKENS | No | Total prompt token limit | 150000 |
| GEMINI_SUMMARIZE_FILES_LIMIT | No | gemini_summarize_files character limit | 800000 |
| CLOUDFLARE_AI_GATEWAY_ENABLED | No | Enable Cloudflare AI Gateway | false |
| CLOUDFLARE_AI_GATEWAY_TIMEOUT | No | Gateway timeout in seconds | 300 |
| OPENROUTER_COST_LIMIT_PER_DAY | No | Daily cost limit in USD | 10.0 |
| GEMINI_CONVERSATION_MAX_TOKENS | No | Token history limit | 20000 |
| GEMINI_SUBPROCESS_MAX_CPU_TIME | No | Subprocess CPU time limit in seconds | 300 |
| GEMINI_SUBPROCESS_MAX_MEMORY_MB | No | Subprocess memory limit in MB | 512 |
| GEMINI_CONVERSATION_MAX_MESSAGES | No | Message history limit | 10 |
| CLOUDFLARE_AI_GATEWAY_MAX_RETRIES | No | Maximum retry attempts | 3 |
| GEMINI_CONVERSATION_EXPIRATION_HOURS | No | Auto-cleanup time in hours | 24 |
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 |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/centminmod/gemini-cli-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server