Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoInterface to bind.0.0.0.0
PORTNoHTTP port for the entire app (API + MCP + SPA).3000
NODE_ENVNoLog level toggle.development
ADMIN_TOKENNoIf set, all /api/* requests require Authorization: Bearer <token>.
AGENT_SECRETNoKey used to encrypt shared credentials (set a strong value in production).change-me-in-production
MEMORY_MAX_MBNoDefault cap on the on-disk size of the knowledge-graph memory store (MB). A GUI/API override is persisted in the settings table and takes precedence. Writes refuse to exceed the budget.100
DISABLED_TOOLSNoComma-separated global tool denylist enforced by centralized policy.
ALLOWED_ORIGINSNoComma-separated origins allowed to call the API. Empty = allow all.
JOB_CONCURRENCYNoNumber of background jobs that may run at once.2
FS_ALLOWED_PATHSNoComma-separated authorized directories agents may read/write/search via the filesystem tools and run git in. Leave empty to disable those tools.
DISCOVERY_ENABLEDNofalse disables startup/scheduled discovery crawling.true
DNS_ALLOWED_HOSTSNoComma-separated authorized names agents may query via DNS (wildcards like example.com.* supported). Leave empty to disable DNS tools.
LLM_REGISTRY_URLSNoComma-separated registry URLs to seed LLM/AI model discovery.
MCP_REGISTRY_URLSNoComma-separated registry URLs to seed MCP server discovery.
SSH_ALLOWED_HOSTSNoComma-separated authorized hosts agents may SSH into. Leave empty to disable the SSH client.
REQUEST_TIMEOUT_MSNoTimeout for outbound HTTP fetches.10000
TOOL_APPROVAL_TOKENNoApproval token required when tool approvals are enforced.
RATE_LIMIT_WINDOW_MSNoWindow length for per-agent/per-tool/provider quotas.3600000
DEFAULT_CACHE_TTL_SECNoDefault TTL for cacheable tool responses.900
DISCOVERY_INTERVAL_MSNoHow often the scheduled discovery runs.21600000
WEBHOOK_SHARED_SECRETNoOptional fallback secret for inbound /hooks/:webhookId calls.
ENFORCE_TOOL_APPROVALSNoIf true, approval-marked tools require approvalToken.false
RESEARCH_WORKER_ENABLEDNoEnable the autonomous research worker schedule and research.run tooling.true
DEFAULT_CALLS_PER_WINDOWNoDefault per-agent quota window enforced by the centralized policy layer.120
NETWORK_DISCOVER_TARGETSNoComma-separated authorized hosts/CIDRs to probe for device discovery, ping, traceroute, and port-scan. Leave empty to disable those tools.
RESEARCH_WORKER_MAX_PAGESNoPer-run cap on how many web-search result pages the worker expands.3
RESEARCH_WORKER_MAX_TOKENSNoApproximate per-run text budget before a non-forced worker run is skipped.12000
RESEARCH_WORKER_INTERVAL_MSNoDefault cadence for the seeded idle-only research worker schedule.1800000
RESEARCH_WORKER_MAX_TIME_MSNoPer-request timeout budget for worker web extraction.20000
SOCKET_ALLOWED_LISTEN_HOSTSNoComma-separated authorized bind hosts for socket.listen (for example 127.0.0.1,localhost).
SOCKET_ALLOWED_LISTEN_PORTSNoComma-separated authorized listen ports or ranges for socket.listen (for example 46000-46010).
RESEARCH_WORKER_ONLY_WHEN_IDLENoRequire operator-idle status and no active MCP sessions before background research runs.true
SOCKET_ALLOWED_CONNECT_TARGETSNoComma-separated authorized socket client hosts. Falls back to NETWORK_DISCOVER_TARGETS when unset.

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

Latest Blog Posts

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/blindengineerMO/MCPMaestro'

If you have feedback or need assistance with the MCP directory API, please join our Discord server