Skip to main content
Glama
Flisk App Builder

Flisk App Builder

Official

resource_create

Destructive

Scaffold a new service with source, Dockerfile and tests, or register an existing directory that already has a service.json. Run it before starting the resource with up.

Instructions

Scaffold a new service (service.json, Dockerfile, source and a test) with flisk resource <name> --yes, or register an existing directory that already has a service.json. Returns the command's text output. Without stack it uses the only existing stack or main, and fails when several stacks exist. Do not call it again for a resource that already exists: that rewrites its service.json and can assign it a new port (check with resource_list first). Call up afterwards to start it. Set projectPath when the MCP server is not running from the project root.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "resource_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesResource name (kebab-case)
portNoPort within the type's range (default: the next free one)
typeNoResource type (default backend). Redis, Qdrant, MinIO, MLflow, MySQL, MongoDB, ClickHouse, NATS, RabbitMQ, Mailpit and stripe-mock are frameworks: type database, queue, storage, mail or payment plus framework
localNoFrontend or backend only: scaffold it to run on this computer with no Docker or Tilt (a plain Vite config, a command in service.json), the way flisk create does by default
stackNoStack to assign the resource to
runtimeNoAgent runtime (type agent only): custom
featuresNoResource features to enable, for example prisma or drizzle
languageNoBackend language: bun (default), python, go, rust, node
frameworkNoFrontend: react (default), vue, svelte, preact, lit, solid, qwik, vanilla, tanstack-router, next. Backend: hono (default), express, elysia, fastify, nestjs, koa, h3. Database: postgres (default, the shared Flisk Postgres), redis, qdrant, mlflow, mysql, mongodb, clickhouse (each its own container; the services that list it in dependsOn get its connection settings). Queue: nats (default), rabbitmq. Storage: minio (default). Mail: mailpit (default, local SMTP and inbox). Payment: stripe-mock (default, Stripe API emulator)
durabilityNoWhere agent sessions are checkpointed (type agent only): files or postgres
projectPathNoAbsolute path to the Flisk project root; run this operation from that directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.4.59
    • changedInput schema / properties / framework / description
      Previous value: -"Frontend: react (default), vue, svelte, preact, lit, solid, qwik, vanilla, tanstack-router, next. Backend: hono (default), express, elysia, fastify, nestjs, koa, h3. Database: postgres (default, the shared Flisk Postgres), redis, qdrant, minio, mlflow, mysql, mongodb, clickhouse (each its own container; the services that list it in dependsOn get its connection settings). Queue: nats (default), rabbitmq"New value: +"Frontend: react (default), vue, svelte, preact, lit, solid, qwik, vanilla, tanstack-router, next. Backend: hono (default), express, elysia, fastify, nestjs, koa, h3. Database: postgres (default, the shared Flisk Postgres), redis, qdrant, mlflow, mysql, mongodb, clickhouse (each its own container; the services that list it in dependsOn get its connection settings). Queue: nats (default), rabbitmq. Storage: minio (default). Mail: mailpit (default, local SMTP and inbox). Payment: stripe-mock (default, Stripe API emulator)"
    • changedInput schema / properties / type / description
      Previous value: -"Resource type (default backend). Redis, Qdrant, MinIO, MLflow, MySQL, MongoDB, ClickHouse, NATS and RabbitMQ are frameworks: type database or queue plus framework"New value: +"Resource type (default backend). Redis, Qdrant, MinIO, MLflow, MySQL, MongoDB, ClickHouse, NATS, RabbitMQ, Mailpit and stripe-mock are frameworks: type database, queue, storage, mail or payment plus framework"
    • changedInput schema / properties / type / enum
      Previous value: -[
      -  "backend",
      -  "frontend",
      -  "worker",
      -  "mcp",
      -  "agent",
      -  "bring-your-own",
      -  "inference",
      -  "database",
      -  "queue"
      -]New value: +[
      +  "backend",
      +  "frontend",
      +  "worker",
      +  "mcp",
      +  "agent",
      +  "bring-your-own",
      +  "inference",
      +  "database",
      +  "queue",
      +  "storage",
      +  "mail",
      +  "payment"
      +]
  2. Changed2 schema fields changedv1.4.42
    • changedInput schema / properties / framework / description
      Previous value: -"Frontend: react (default), vue, svelte, preact, lit, solid, qwik, vanilla, tanstack-router, next. Backend: hono (default), express, elysia, fastify, nestjs, koa, h3. Database: postgres (default, the shared Flisk Postgres), redis, qdrant, minio, mlflow (each its own container; the services that list it in dependsOn get its connection settings). Queue: nats (default), rabbitmq"New value: +"Frontend: react (default), vue, svelte, preact, lit, solid, qwik, vanilla, tanstack-router, next. Backend: hono (default), express, elysia, fastify, nestjs, koa, h3. Database: postgres (default, the shared Flisk Postgres), redis, qdrant, minio, mlflow, mysql, mongodb, clickhouse (each its own container; the services that list it in dependsOn get its connection settings). Queue: nats (default), rabbitmq"
    • changedInput schema / properties / type / description
      Previous value: -"Resource type (default backend). Redis, Qdrant, MinIO, MLflow, NATS and RabbitMQ are frameworks: type database or queue plus framework"New value: +"Resource type (default backend). Redis, Qdrant, MinIO, MLflow, MySQL, MongoDB, ClickHouse, NATS and RabbitMQ are frameworks: type database or queue plus framework"
  3. Changed1 schema field changedv1.4.37
    • addedInput schema / properties / local
      Added value: +{
      +  "description": "Frontend or backend only: scaffold it to run on this computer with no Docker or Tilt (a plain Vite config, a command in service.json), the way flisk create does by default",
      +  "type": "boolean"
      +}
  4. Changed3 schema fields changedv1.4.33
    • changedInput schema / properties / framework / description
      Previous value: -"Frontend: react (default), vue, svelte, preact, lit, solid, qwik, vanilla, tanstack-router, next. Backend: hono (default), express, elysia, fastify, nestjs, koa, h3"New value: +"Frontend: react (default), vue, svelte, preact, lit, solid, qwik, vanilla, tanstack-router, next. Backend: hono (default), express, elysia, fastify, nestjs, koa, h3. Database: postgres (default, the shared Flisk Postgres), redis, qdrant, minio, mlflow (each its own container; the services that list it in dependsOn get its connection settings). Queue: nats (default), rabbitmq"
    • changedInput schema / properties / type / description
      Previous value: -"Resource type (default backend)"New value: +"Resource type (default backend). Redis, Qdrant, MinIO, MLflow, NATS and RabbitMQ are frameworks: type database or queue plus framework"
    • changedInput schema / properties / type / enum
      Previous value: -[
      -  "backend",
      -  "frontend",
      -  "worker",
      -  "mcp",
      -  "agent",
      -  "bring-your-own",
      -  "inference",
      -  "redis",
      -  "qdrant",
      -  "rabbitmq",
      -  "database"
      -]New value: +[
      +  "backend",
      +  "frontend",
      +  "worker",
      +  "mcp",
      +  "agent",
      +  "bring-your-own",
      +  "inference",
      +  "database",
      +  "queue"
      +]
  5. Changed1 schema field changedv1.4.25
    • changedInput schema / properties / type / enum
      Previous value: -[
      -  "backend",
      -  "frontend",
      -  "worker",
      -  "mcp",
      -  "agent",
      -  "bring-your-own"
      -]New value: +[
      +  "backend",
      +  "frontend",
      +  "worker",
      +  "mcp",
      +  "agent",
      +  "bring-your-own",
      +  "inference",
      +  "redis",
      +  "qdrant",
      +  "rabbitmq",
      +  "database"
      +]
  6. First observedv1.4.17

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the destructiveHint=true annotation, the description explains exactly what damage re-invocation causes (rewrites service.json, can reassign the port), discloses a failure mode (fails when several stacks exist with no stack argument), states stack defaults, and states the return format (the command's text output). This is well past what the annotations carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then defaults, then the hazard warning, then the follow-up — a logical order. It is dense with six sentences and the CLI invocation snippet is slightly extraneous for an agent caller, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter destructive scaffold tool with no output schema, the description covers the create-vs-register fork, defaults, failure modes, return value, and the cross-tool workflow. Nothing an agent needs before calling is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real meaning on top: the `stack` parameter's defaulting rule and failure condition, and when `projectPath` matters (server not running from project root). It does not explain the port, type, or framework interactions, but those are already fully documented in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb pair (scaffold a new service / register an existing directory) and names the concrete artifacts produced (service.json, Dockerfile, source, test). This distinguishes it cleanly from resource_list and up, which are named later in the text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-not guidance ('Do not call it again for a resource that already exists'), names the verification step (check with resource_list first), and names the follow-up action ('Call `up` afterwards to start it'). The alternative path for an existing directory with a service.json is also spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.