Flisk App Builder
OfficialServer 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.
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| doctorA | Check whether this machine can run the Flisk stack (Docker, Tilt, ports). Read-only. Optionally set projectPath to include checks for a specific Flisk project. Returns data.ready and data.host.canUp; run it before |
| upA | Start the stack (or part of it) detached from the optional projectPath. The result carries |
| downA | Stop the running stack, optionally selecting its project with projectPath. It stops the running services and does not edit the project's files. Use |
| statusA | Show the live state of the stack: its stacks, resources, their ingress URLs and container ports, the stack-level ports, and Tilt readiness (data.tilt.readiness: ready, pending, failures, enabled; null when no Tilt answers). Read-only. Poll it after |
| logsA | A bounded snapshot of recent logs from the running stack (default the last 200 lines, at most 10000), returned as text. Read-only. Optionally select the project with projectPath. Not a stream: call it again for newer lines. Use |
| resource_listA | List the selected project's services (resources) with their stack, type and port, whether or not they are running. Read-only. Use |
| resource_restartA | Restart one running resource in the stack along with any active container resources that transitively declare |
| resource_runA | Run a one-off command (a seed script, a migration, a status check) with the environment one resource has in the stack, and return its exit code, stdout and stderr (the last 64 KB of each; values from the project's .env files are masked). It runs any command, so it is refused unless confirm is true: ask the user first. A container resource must be running (start it with |
| agent_listA | List AI agent resources (appType: 'agent') in the project with their stack, runtime, durability and port. Read-only. Use |
| agent_sessionsA | List the sessions of a running AI agent resource (id, last activity, status, checkpoint size), or read one session's checkpoint when sessionId is set. Set projectPath when the MCP server is not running from the project root. |
| stack_listA | List the project's stacks with their resource counts. Read-only. Use |
| project_infoA | Project root, whether the generated master files exist (data.configured, data.missingFiles), and resource and stack counts. Read-only; a quick first call to learn whether a folder is a configured Flisk project. Use |
| project_templatesA | List the starter templates project_init can clone (data.templates): each one's key, repo, description and, for a template pinned to a commit, the ref it checks out. Read-only; the same rows as |
| network_listA | The Traefik URL of every frontend and API service, with its base path, port and whether it answers (running, stopped). Read-only. Use it to find where to open a service; use |
| config_verifyA | Check that the generated files match .flisk/project.json and that every service.json is valid. Returns data.valid, data.errors, data.warnings and data.diffs; a drifted generated file is fixed with config_regenerate. Set projectPath when the MCP server is not running from the project root. |
| config_explainA | Explain one project file: whether Flisk generated it or the user owns it, its source, whether it is edited now, whether editing it blocks |
| runtime_checkA | Read-only. Check that the installed Flisk CLI has its bundled runtime assets (engine, templates). Returns ok, assetRoot and what is missing; a source checkout reports ok: false because the assets exist only in a packaged install. projectPath is optional: a project-local install under its node_modules is checked too. |
| config_regenerateA | Regenerate the master config files in .flisk/.flisk-out/ from .flisk/project.json. A dry run by default, which returns the planned changes as data.changes (each file's status and lineDiff) with data.hasChanges; set dryRun to false to write them and get the same list, which discards hand edits in those generated files. Set projectPath when the MCP server is not running from the project root. |
| resource_createA | Scaffold a new service (service.json, Dockerfile, source and a test) with |
| tool_addA | Add a tool by its everyday name (react, nextjs, fastapi, nodejs, postgresql, mysql, mongodb, rag, embeddings, llm-api) with |
| stack_assignA | Assign resources that have no stack yet to a stack (writes |
| project_initA | Create a Flisk project with |
| project_ejectA | Write EJECTED.md with |
| project_importA | Import the services in a directory's root docker-compose.yml as bring-your-own service.json files with |
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 24 tools
The set has several look-alike families (status/resource_list/network_list/stack_list/agent_list/project_info, and doctor/runtime_check/config_verify), but the descriptions explicitly cross-reference each other with 'use X for Y' guidance, which resolves most confusion. A few boundaries (doctor vs runtime_check, project_info vs config_verify) still require careful reading.
The dominant convention is noun_verb (project_init, resource_create, config_regenerate, stack_assign, agent_sessions, network_list), applied to 19 of 24 tools. The remaining five are bare lifecycle verbs (up, down, status, logs, doctor), which is a deliberate and readable deviation but not fully uniform.
24 tools is on the heavy side, but the domain is genuinely broad: project scaffolding/import/eject, config generation and verification, stack lifecycle, resource management, agents, and host checks. Nearly every tool maps to a distinct operation, though a few (project_templates, config_explain, runtime_check) are niche.
Creation and inspection are well covered (project_init/import, resource_create, tool_add, up/down/restart/run), but there is no delete or remove operation for resources or stacks, no per-service stop, and agent tooling is read-only (list/sessions) with no lifecycle control. These gaps will force agents to fall back to raw CLI calls.