Skip to main content
Glama
shapez 1 游玩 MCP

shapez 1 游玩 MCP

by aymidasing

game

Inspect and control a running shapez 1.5.6 save: query entities, resources and flow, then place belts, wires and blueprints, trace production and check signals through the CDP debugging port.

Instructions

select(id=活动档 internalId) 绑定写入;layer 切 E 视角;trace(at) 查上游堵点;check_signals(tiles,reference 或 network,pin,value) 只报异常;hub/speeds/catalog/building/path/flow 查询;place(items)/remove(tiles 或 region)/route(route)/wire(route,color,join)/blueprint(capture 或 paste)/configure/upgrade。坐标 [x,y]。

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": {
      "op": "<op>"
    },
    "name": "game"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNo
dxNo
dyNo
idNo
opYes
pinNo
joinNo
colorNo
itemsNo
layerNo
routeNo
tilesNo
valueNo
handleNo
regionNo
networkNo
targetsNo
portableNo
rotationNo
blueprintNo
emptyOnlyNo
referenceNo
requestIdNo
routeCodeNo
referencePinNo
blueprintModeNo

Output Schema

NameRequiredDescriptionDefault
dataNo
errorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.4/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false and openWorldHint=false, so the agent knows this mutates a closed world; the description does not go beyond that to say what is destroyed, whether remove/place are reversible, what 'select ... 绑定写入' binding actually persists, or that 'save' commits state. It does add one useful behavioral note that check_signals reports only anomalies, but for a 21-op mutating dispatcher this is far too thin. No contradiction with the annotations.

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

Conciseness2/5

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

It is short, but it is one run-on sentence of semicolon-separated fragments mixing Chinese and English abbreviations, with no front-loaded statement of what the tool is. The density is compression, not conciseness: the agent has to parse 'hub/speeds/catalog/building/path/flow 查询' as a bundle of unrelated read ops rather than as structured information.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the op enum in the schema backs up the description's op list. But with 26 parameters, zero schema descriptions, and only one required field, the definition leaves an agent unable to determine which parameters each op needs or what the mutating ops do; a per-op parameter mapping is the missing piece.

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

Parameters2/5

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

Schema description coverage is 0% across 26 parameters, so the description carries the full burden, and it only skims surface names (id, layer, at, tiles, reference, network, pin, value, items, route, color, join, region) without explaining meaning, units, ranges, or requiredness per op. It does add the coordinate convention '[x,y]' and one gloss that id is the '活动档 internalId', but pin ranges 0-15, join semantics, emptyOnly, portable, targets, handle, and requestId are left entirely opaque.

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

Purpose3/5

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

The description does enumerate concrete operations (select, place, remove, wire, blueprint, trace, check_signals, etc.) over a game/grid resource, so the general purpose of a multi-op game-world mutator is inferable. But the tool name 'game' carries no information, and the ops are listed as terse bilingual fragments ('layer 切 E 视角', 'trace(at) 查上游堵点') rather than a stated purpose. An agent must decode the string to know what the tool is for.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance, no when-not, and no routing to siblings such as apply_belts, preview_belts, sample_flow, or screenshot, even though those clearly overlap with the belt/flow/signal operations listed here. The only usage-shaped hints are micro-notes like 'check_signals ... 只报异常' (only reports anomalies) and 'select ... 绑定写入' (binds subsequent writes), which are implied behavior rather than selection guidance.

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