Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SYLVE_NODENoDefault target cluster node.
SYLVE_TOKENNoOverride bearer token without a saved context.
SYLVE_CONFIGNoOverride configuration file path (default: ~/.config/sylve/config.yaml).
SYLVE_SERVERNoOverride server URL without a saved context.
SYLVE_CONTEXTNoOverride active context name.
SYLVE_SWAGGERNoOverride the bundled swagger.json path.
SYLVE_INSECURENoSet to 1, true, or yes to skip TLS verification.
SYLVE_READ_ONLYNoSet to 1, true, or yes to enforce read-only mode.
XDG_CONFIG_HOMENoBase directory for the default configuration file.

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
sylve_whoamiA

Show the active Sylve login context, user, node, and JWT expiry status.

sylve_context_listA

List configured Sylve login contexts from ~/.config/sylve/config.yaml.

sylve_cluster_statusA

Show cluster status: Raft leader, quorum members, node health, and guest counts.

sylve_cluster_resourcesA

List every VM, Jail, and template across all cluster nodes.

sylve_node_listA

List all cluster nodes with CPU%, RAM%, disk, guest counts, and version.

sylve_node_showA

Show detailed CPU/RAM/swap/disk telemetry for a node (defaults to the connected node).

sylve_node_audit_logsA

Show recent audit records from a node (or all nodes) with parsed request paths.

sylve_node_drainA

Build and optionally execute a maintenance drain plan for a node (HA failover, migration, or stop). Dry run by default for safety.

sylve_vm_listB

List Bhyve VMs across the cluster.

sylve_vm_showA

Show a VM's full configuration, live state, and guest-agent IP addresses.

sylve_vm_createB

Provision a Bhyve VM from scratch or from a template. Parses sizes like '2G', auto-allocs RID and VNC port, validates cloud-init YAML. Supports dry_run.

sylve_vm_actionB

Start, stop, shutdown, reboot, or restart one or more VMs by name or RID.

sylve_vm_migrateB

Validate and live-migrate a VM to another cluster node.

sylve_vm_deleteC

Delete a VM and optionally its volumes, raw disks, and MAC objects.

sylve_vm_logsB

Retrieve a VM's serial console log output.

sylve_vm_snapshotB

List, create, roll back, or delete VM ZFS snapshots.

sylve_vm_templateC

List, show, capture, deploy, or delete VM templates.

sylve_jail_listB

List FreeBSD Jails across the cluster.

sylve_jail_showA

Show a Jail's full configuration and live guest info.

sylve_jail_createC

Create a FreeBSD Jail on a ZFS pool.

sylve_jail_actionC

Start, stop, or restart one or more Jails by CTID or name.

sylve_jail_migrateC

Validate and migrate a Jail to another cluster node.

sylve_jail_deleteB

Delete a Jail, optionally removing its rootfs and MAC objects.

sylve_jail_logsA

Retrieve a Jail's console log output.

sylve_jail_snapshotC

List, create, roll back, or delete Jail ZFS snapshots.

sylve_jail_bootstrapC

List, create, or delete pkgbase FreeBSD jail bootstraps on a ZFS pool.

sylve_jail_templateC

List, show, capture, deploy, or delete jail templates.

sylve_zfs_poolC

List, inspect, or scrub ZFS storage pools (resolves pool names to GUIDs).

sylve_zfs_datasetC

List, create, edit, or delete ZFS filesystems and volumes.

sylve_zfs_snapshotC

List, create, roll back, or delete ZFS snapshots, plus periodic snapshot jobs.

sylve_downloadB

List, show, queue URL downloads, or delete ISOs/images on the downloader.

sylve_network_overviewB

Query one network subsystem (interfaces, switches, routes, DHCP, firewall, objects, WireGuard).

sylve_replicationC

Manage HA replication policies, events, and failovers.

sylve_backupC

Inspect backup targets, jobs, and events; run or restore backups.

sylve_taskC

List, show, or wait on guest lifecycle tasks; cancel migrations.

sylve_api_searchA

Search all Sylve Swagger operations by keyword, tag, or HTTP method. Use this to discover any of the 441 endpoints before calling them.

sylve_api_schemaA

Show the full request/response schema (with $refs resolved) for one Swagger operation. Use sylve_api_search to find the operation first.

sylve_api_callB

Execute any documented Sylve API operation directly (GET/POST/PUT/PATCH/DELETE). Combine with sylve_api_schema to build accurate bodies. Filters out None query params.

Prompts

Interactive templates invoked by user choice

NameDescription
triage-clusterInspect cluster health: offline nodes, failed tasks, and ZFS pool status.
plan-node-drainBuild a dry-run maintenance drain plan for a node and flag blocked guests or pinned backup jobs.

Resources

Contextual data attached and managed by the client

NameDescription
Cluster statusLive Sylve cluster and Raft status JSON.
Cluster resourcesAll VMs, Jails, and templates across cluster nodes.
OpenAPI tag summaryAll Swagger tags and their operation counts.

TDQS

B3.1/5.0

Scored across 38 tools

Disambiguation4/5

Most tools target a clearly distinct resource and action (VM, jail, ZFS, node, backup, replication, task). A few boundaries are blurry: VM/jail/ZFS snapshot tools overlap in concept, and sylve_api_call can duplicate nearly any operation, but the descriptions make the intended scope clear.

Naming Consistency4/5

The sylve_ prefix and resource-based grouping are consistent across the set (sylve_vm_list, sylve_vm_show, sylve_jail_create, etc.). Minor deviations are the noun-only multi-action tools such as sylve_zfs_pool, sylve_vm_snapshot, and sylve_network_overview, which omit the verb but remain readable.

Tool Count2/5

At 38 tools, the surface is heavy for a single MCP server and exceeds the typical comfortable range. While the domain is broad, several tools could be consolidated or scoped further, and the three api_* meta-tools plus multiple resource-specific lifecycle tools inflate the count.

Completeness4/5

Core lifecycle coverage is strong across VMs, jails, ZFS, backups, replication, tasks, and cluster/node operations. Minor gaps exist around explicit network mutation, user/context creation, and some fine-grained operations, but sylve_api_search/schema/call provide a workaround via the full Swagger surface.

Maintenance

ActivityMaintained
ResponsivenessNo issues