Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AI_MODELNoClaude model used for suggestionsclaude-opus-5-5
API_HOSTNoAddress the server binds to. Set `0.0.0.0` to serve other machines (e.g. in a container)127.0.0.1
API_PORTNoPort the server listens on8080
APP_NAMENoAPI title shown in Swagger UINameInsight
AI_EFFORTNoEffort level for suggestions (`low`, `medium`, `high`)medium
DNS_SERVERSNoComma-separated DNS server IPs, e.g. `1.1.1.1,8.8.8.8`. Default is the system resolvers. Set this when the host's resolver also answers for internal zones
CORS_ORIGINSNoComma-separated origins allowed to call the API from a browser, e.g. `https://app.example.com`. Empty means no cross-origin access
LOG_REQUESTSNoSet to `false` to turn off the per-request access logtrue
ALLOWED_HOSTSNoComma-separated Host headers the server accepts (DNS-rebinding protection). Empty: localhost names only on a loopback bind, any host otherwise (with a startup warning). `MCP_ALLOWED_HOSTS` is an older alias
DNS_TIMEOUT_MSNoDNS query timeout5000
MAX_BODY_BYTESNoMaximum JSON / form body size16384
RATE_LIMIT_MAXNoRequests allowed per client IP per window on `/api/*`30
RDAP_TIMEOUT_MSNoHard deadline per RDAP request5000
MAX_UPLOAD_BYTESNoMaximum uploaded file size65536
TRUST_PROXY_HOPSNoNumber of reverse proxies in front of the service. Set this behind a load balancer so rate limiting uses the real client IP0
WHOIS_TIMEOUT_MSNoHard deadline per WHOIS server (a lookup can follow up to 2 referrals)10000
ANTHROPIC_API_KEYNoSecret. Enables REST AI suggestions (and the MCP fallback). Set only in the environment; never commit
LOOKUP_BUDGET_MAXNoDomains each client IP may look up per window (a bulk request costs one per domain)200
LOOKUP_CONCURRENCYNoDomains looked up at the same time within one request5
MAX_QUEUED_LOOKUPSNoLookups allowed to wait for a slot; beyond this, requests get `503` + `Retry-After`100
SHUTDOWN_TIMEOUT_MSNoOn SIGTERM/SIGINT, how long in-flight requests may finish before connections are force-closed10000
PING_TIMEOUT_SECONDSNoPing reply timeout2
RATE_LIMIT_WINDOW_MSNoRate-limit window in milliseconds60000
WEB_CHECK_TIMEOUT_MSNoHard deadline for the `insights` HTTPS check5000
MAX_CONCURRENT_LOOKUPSNoDomains looked up at the same time across all requests20
SUGGEST_RATE_LIMIT_MAXNoSuggestion requests per client IP per rate-limit window (REST and MCP combined)5
LOOKUP_BUDGET_WINDOW_MSNoLookup-budget window in milliseconds60000
MAX_CONCURRENT_AI_CALLSNoClaude API calls in flight at once2
MAX_DOMAINS_PER_REQUESTNoMaximum domains in one bulk request50
MAX_RDAP_RESPONSE_BYTESNoLarger RDAP responses are discarded262144
MAX_WHOIS_RESPONSE_BYTESNoWHOIS responses longer than this are truncated131072
GLOBAL_SUGGEST_MAX_PER_HOURNoClaude API suggestion calls per hour for the whole process (caps spend on the server key)100
MAX_CONCURRENT_REQUESTS_PER_CLIENTNoRequests one client IP may have in flight on `/api` and `/mcp`2

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources