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 |
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 | |