Skip to main content
Glama
wfbcargo

spawn-mcp

by wfbcargo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

spawn_push

Push game changes live to every open room, staging and committing on engine 6.0+ git worlds, or compiling and uploading specs on older document worlds.

Instructions

Push your work live (~1s in every open room). The lane is detected from the world's engine. ON ENGINE 6.0+ (git lane) this stages, commits and git-pushes the clone: message is REQUIRED and is not a log line — its first line lands in the creator's chat and their changes list under your name, so write one plain sentence about what changed for the PLAYER ("the getaway car keeps its grip on wet streets"), never how you did it, never a file or a function; put the how in body, which is also where you leave Savi what she needs. The result carries the remote: verdict lines — rooms, players, and each room's reading of your change. A push refused as non-fast-forward means origin moved: spawn_latest, then push again. ON A PRE-6.0 WORLD (document lane) it is unchanged: compile the project and PUT the spec; on 409 version_conflict call spawn_latest, merge .theirs receipts and push again. In team mode document-lane pushes are serialised and rebased onto head first. Either way a successful push proves it parsed, nothing more — look at spawn_play_screenshot before calling the work done, and if what you pushed is visual and untextured or plainly styled, the missing piece is a skill you did not load (spawn_skill ids: drawn-art, custom-materials, looks, game-ui); spawn_audit_ui answers the other question, what UI you never built at all.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoEngine 6.0+ only: the commit body — the how, and anything Savi needs. She reads it on the creator's next turn; there is no other door into her chat.
forceNoDocument lane only: whole-replace without base-version rail / discard .theirs (destructive)
dryRunNoDocument lane: validate the push without saving. Git lane: run the local pre-flight and report what WOULD be committed, without committing or pushing.
messageNoEngine 6.0+ ONLY, and required there: the commit's first line, which IS the creator's chat line. One plain sentence about what changed for the player — "the tram now stops at the north platform". Not a file, not a function, not a diagnosis. Ignored on the document lane.
projectDirNoAbsolute path to the Spawn game project (game.json / .env). Defaults to SPAWN_PROJECT_DIR or the MCP process cwd.
engineVersionNoOptional engine version this call assumes: a semver ('6.0.0', '5.4') or an era name ('6.0' for a git world, 'document' for a pre-6.0 one). Omit it and the world's engine is detected from the API and cached. When passed it is CHECKED against the real pin and a mismatch fails the call without writing anything — it is an assertion, not an override.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.0.0
    • addedInput schema / properties / body
      Added value: +{
+  "description": "Engine 6.0+ only: the commit body — the how, and anything Savi needs. She reads it on the creator's next turn; there is no other door into her chat.",
+  "type": "string"
+}
    • addedInput schema / properties / dryRun / description
      Added value: +"Document lane: validate the push without saving. Git lane: run the local pre-flight and report what WOULD be committed, without committing or pushing."
    • addedInput schema / properties / engineVersion
      Added value: +{
+  "description": "Optional engine version this call assumes: a semver ('6.0.0', '5.4') or an era name ('6.0' for a git world, 'document' for a pre-6.0 one). Omit it and the world's engine is detected from the API and cached. When passed it is CHECKED against the real pin and a mismatch fails the call without writing anything — it is an assertion, not an override.",
+  "type": "string"
+}
    • changedInput schema / properties / force / description
      Previous value: -"Whole-replace without base-version rail / discard .theirs (destructive)"New value: +"Document lane only: whole-replace without base-version rail / discard .theirs (destructive)"
    • addedInput schema / properties / message
      Added value: +{
+  "description": "Engine 6.0+ ONLY, and required there: the commit's first line, which IS the creator's chat line. One plain sentence about what changed for the player — \"the tram now stops at the north platform\". Not a file, not a function, not a diagnosis. Ignored on the document lane.",
+  "minLength": 1,
+  "type": "string"
+}
  2. First observedv1.2.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: it discloses lane detection from the world's engine, that `message` is REQUIRED on 6.0+ and lands in the creator's chat, that `body` is the only door into Savi's chat, that pushes are serialised/rebased in team mode, and that 'a successful push proves it parsed, nothing more'. It also warns that a refused non-fast-forward means origin moved.

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?

The purpose is front-loaded and nearly every clause carries operational weight (latency, error paths, chat-line rules). It is very dense and mixes usage, semantics and follow-ups into one block, which hurts scanability, but there is little padding.

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 a complex, annotation-free, no-output-schema tool spanning two engine lanes and six parameters, the description covers both code paths, the required-field asymmetry, the result's `remote:` verdict lines, and the correct follow-up checks. Nothing an agent needs to call it correctly appears to be 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, but the description adds genuine meaning beyond the schema: `message` is explicitly framed as the creator's chat line rather than a log line, with content rules ('never how you did it, never a file or a function'), and `body` is explained as the channel for the how and for Savi. `force`/`dryRun` semantics are left to 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?

The opening sentence states a concrete verb and resource ('Push your work live') plus scope ('~1s in every open room'), and the body distinguishes this tool from spawn_latest, spawn_play_screenshot, spawn_skill and spawn_audit_ui by name. An agent can tell what it does and how it differs from siblings without opening any schema.

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?

It gives explicit when-to-use guidance for both engine eras, names the recovery path for two failure modes (non-fast-forward -> spawn_latest then re-push; 409 version_conflict -> spawn_latest, merge .theirs receipts, push again), and routes the agent to sibling tools for the questions this tool does not answer (spawn_play_screenshot, spawn_audit_ui, spawn_skill). Little is left to inference.

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

Deploy Server

Other Tools