Skip to main content
Glama
hoklims

material-workbench

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tasks
{
  "list": {},
  "cancel": {},
  "requests": {
    "tools": {
      "call": {}
    },
    "prompts": {
      "get": {}
    },
    "resources": {
      "read": {}
    }
  }
}
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
initializeC

Handshake. Returns sidecar version + cache_root + capabilities.

shutdownC

Returns {ok: true}. Client-side disconnect is the actual close.

workspace_setA

Change workspace_root at runtime. Pass null to clear.

archetype_listA

List all registered archetypes with their params and modifiers.

recipe_readB

Read a recipe JSON file. scope must be 'workspace' or 'app_data'.

recipe_writeC

Write a recipe to disk after normalization. Returns render_hash.

recipe_normalizeB

Normalize a recipe (clamp params, derive seeds, recompute hash).

recipe_validateC

Validate a recipe. Returns {valid: bool, errors: list}.

recipe_mutateC

Apply patches [{param_path, value}], re-normalize, return new hash.

render_runC

Render a recipe. Returns manifest + render_source enum.

render_cancelA

Cancel a render request. Idempotent.

cache_lookupB

Look up a cached manifest by render_hash.

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/hoklims/material-workbench'

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