tugport
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Tugport deploys and runs services on this server. Address services as project.service. Deploys wait for the result by default.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_projectsA | List projects you can see, with your role in each. |
| get_projectC | A project's services with live status, and its shared variable names. |
| create_projectC | Create a project. |
| create_serviceB | Create a service in a project. kind is app, database or compose. For apps pass spec.source ({type: git, repo, branch} | {type: image, image} | {type: dockerfile, content}); for databases pass database: {engine: postgres|mysql|mariadb|mongo|redis}. |
| get_serviceC | A service's spec, live status, replicas, domains, env var names and last deploy. |
| update_serviceA | Change a service's settings with a JSON merge patch of its spec. Redeploy to apply. |
| delete_serviceA | Delete a service (needs the destroy grant). volumes=true also deletes its data. |
| deployA | Deploy a service and wait for the result (set wait=false to return immediately). Returns the deploy and the end of its log. |
| list_deploysC | Recent deploys of a service. |
| get_deployC | A deploy with its full log. |
| cancel_deployB | Cancel a running or queued deploy. |
| rollbackC | Roll back to the previous version (or a given deploy_id). |
| restartC | Restart a service's containers. |
| stopC | Stop a service. |
| startB | Start a stopped service. |
| get_logsB | Search a service's logs. q is a case-insensitive substring; since/until are epoch milliseconds. |
| execB | Run a shell command inside a service's running container (with its env) and return the output. |
| list_envC | A service's env var names (values only if you hold secrets:read). |
| set_envB | Set or delete env vars: vars is {NAME: "value" or null}. Redeploy to apply. |
| add_domainA | Serve a service on a domain with automatic HTTPS. The host may be a wildcard (*.example.com); several services, even in other projects, can share a host on different path prefixes, and the longest prefix wins. |
| remove_domainC | Remove a domain by id. |
| list_servicesB | Every service you can see across projects, with its state. |
| list_serversC | The servers in this setup (the panel's own is id local) with status, versions and size. |
| server_statusA | A server's current CPU, memory, disks, network, GPUs and per-service usage (default: the panel's own). |
| metricsA | Time series for a server (scope=host), a GPU (gpu:0) or a service (service:, added up over every server). range is 1h, 6h, 24h, 7d or 30d. |
| list_replicasC | A database's read replicas and whether they follow it. |
| add_replicaA | Add a read replica to a database, on a given server or region (placement {node, region, labels}). MongoDB and MariaDB primaries restart once the first time. |
| promote_replicaA | Make a replica a primary when its primary is lost (admin). The old primary's URL variable then points at it. |
| list_backupsC | Backup jobs with their last run. A volume job's volume is a named volume, or a folder of the server (a path) the service mounts. |
| run_backupC | Run a backup job now. |
| backup_runB | A backup or restore run: its status, progress while it runs, and its log. |
| audit_logC | Who did what, newest first. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 32 tools
Most tools map cleanly to a resource+action (list_projects vs get_project, add_replica vs promote_replica, deploy vs list_deploys). The main confusion risks are the near-identical pair run_backup (trigger a job now) versus backup_run (fetch a run's status/log), and the metric/snapshot trio list_servers/server_status/metrics, which requires reading descriptions to separate. Overall mostly distinct with one or two confusable pairs.
A verb_noun pattern dominates (list_projects, create_service, cancel_deploy, get_logs), but it is broken by bare verbs (deploy, restart, stop, start, exec, rollback), noun-only tools (metrics, server_status, audit_log), and the reversed order in backup_run next to run_backup. Still readable, but no single predictable convention lets an agent infer names.
32 tools is heavy and beyond the comfortable range, though the surface spans many genuinely different domains (projects, services, deploys, env, domains, replicas, backups, servers, metrics, audit). Some consolidation is possible — start/stop/restart overlap as a single lifecycle concern, and run_backup/backup_run could be merged — but each domain carries roughly three tools, so it is large rather than bloated.
Core workflows are covered end to end: service CRUD, deploy lifecycle including cancel/rollback, env, domains, logs, exec, and backups. Notable gaps cause dead ends: no way to create or edit a backup job (only list/run), no remove/demote replica despite add/promote, no delete or update project, and no member/role management even though roles appear in list_projects and grant checks gate deletes.