Skip to main content
Glama
wfbcargo

spawn-mcp

by wfbcargo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

spawn_savi

Hand off work to Savi, the in-game AI companion, which fans it out across up to 8 sub-agents for parallel execution. Use it also to post context after pushes.

Instructions

Write into the creator's studio chat, where Savi (their in-game AI companion) reads it. Two uses, and the second is the valuable one. (1) Context after a meaningful push, so you don't fight over the world. (2) HAND OFF WORK: pass task and Savi can take it on, fanning it out across its own sub-agents — up to 8 in the studio, needing no bootstrap key, worktree, or browser of its own. Check spawn_savi_status first: it counts the lanes already burning, and every idle one is a sub-agent that would be finishing work while you build. The strongest targets are the ones where your own lane is weakest: you make art by naming a cdn/ path, and that path is spent on first fetch and cannot be re-rolled, so art that needs iterating — or that the creator wants to steer — is better handed to Savi, who can try it again with them in the loop. Delegate BROAD and GENERAL ("build out the northern district"), never as a step list — the splitting is what the fan-out is good at, and a narrow task wastes it. NOTHING COMES BACK: no reply, no acknowledgement, no completion event, and no endpoint on this API reports who pushed. So declare your boundary with keepOff rather than asking for one, and never put a delegated task on your own critical path. Uptake is visible even though acknowledgement is not: spawn_savi_status shows a new wisp lighting up and what Savi has it doing, which tells you the fan-out started — not that it started on YOUR task, since nothing here reports an author. Detect the finished work by inference rather than by reading a field — head moving past your own last push (spawn_status remote.headVersion) is Savi or the creator, and in team mode spawn_team_status recentPushes is what rules out a teammate. Then spawn_latest to take it and LOOK at it: work arriving on your rail is unverified until you screenshot it, exactly like your own.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskNoWork to hand over, stated broadly, e.g. "Give the north canyon a night pass — lighting, ambient audio, and whatever set dressing sells it." Omit for a pure status note.
keepOffNoAreas you are still working in, so Savi routes its sub-agents around you, e.g. ["scripts/player/**", "world.terrain"]. Advisory — the same trust model as spawn_team_claim.
messageYesWhat just happened, e.g. "Pushed v12: parkour course in the north canyon. Atmosphere untouched if you want it."
subAgentsNoPin how wide Savi should fan the task out (the studio allows up to 8; 1 asks it NOT to split). Omit to let Savi split it as far as it splits, which is usually the better ask.
projectDirNoAbsolute path to the Spawn game project (game.json / .env). Defaults to SPAWN_PROJECT_DIR or the MCP process cwd.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.0.0
    • addedInput schema / properties / keepOff
      Added value: +{
+  "description": "Areas you are still working in, so Savi routes its sub-agents around you, e.g. [\"scripts/player/**\", \"world.terrain\"]. Advisory — the same trust model as spawn_team_claim.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / message / description
      Previous value: -"e.g. \"Pushed v12: parkour course in the north canyon. Atmosphere untouched if you want it.\""New value: +"What just happened, e.g. \"Pushed v12: parkour course in the north canyon. Atmosphere untouched if you want it.\""
    • addedInput schema / properties / message / minLength
      Added value: +1
    • addedInput schema / properties / subAgents
      Added value: +{
+  "description": "Pin how wide Savi should fan the task out (the studio allows up to 8; 1 asks it NOT to split). Omit to let Savi split it as far as it splits, which is usually the better ask.",
+  "maximum": 8,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / task
      Added value: +{
+  "description": "Work to hand over, stated broadly, e.g. \"Give the north canyon a night pass — lighting, ambient audio, and whatever set dressing sells it.\" Omit for a pure status note.",
+  "type": "string"
+}
  2. First observedv1.2.0

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so richly: 'NOTHING COMES BACK: no reply, no acknowledgement, no completion event,' plus 'no endpoint on this API reports who pushed' and no author attribution. It explains how to detect uptake (wisp lighting up in spawn_savi_status) and how to infer completion (remote.headVersion advancing, spawn_team_status recentPushes). This is exactly the non-obvious mutation/side-effect context an agent needs.

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

Conciseness3/5

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

The purpose is front-loaded, which is good, but the body is a dense wall of prose with repetition and asides (the status-detection recipe, the art-path tangent, the re-statement of 'nothing comes back'). Most sentences earn their place, but the block could be tightened considerably without losing meaning.

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 non-standard, annotation-free tool with no output schema, the description covers everything an agent needs: what happens side-effect-wise (no reply/ack), how to verify the work landed, where to look for status, and the constraint against blocking your own critical path. Nothing material 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 schema already documents all five parameters and a baseline of 3 applies. The description adds genuine meaning beyond it: `task` must be 'BROAD and GENERAL... never as a step list' because the fan-out does the splitting, and `keepOff` declares your own boundary under the advisory 'spawn_team_claim' trust model. It also implicitly frames `subAgents` by describing the fan-out default. Slightly more value than the schema baseline.

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

Purpose4/5

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: 'Write into the creator's studio chat, where Savi (their in-game AI companion) reads it.' It distinguishes itself from the related 'spawn_savi_status' by telling the agent to check that first. The purpose is clear, though the 'write' framing is metaphorical enough that the real action (posting a message/task for an AI agent to pick up) only becomes fully explicit several sentences in.

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 cases ('(1) Context after a meaningful push'; '(2) HAND OFF WORK'), a precondition ('Check spawn_savi_status first'), a boundary instruction ('never put a delegated task on your own critical path'), and guidance on target selection ('the ones where your own lane is weakest'). It also names the sibling tools to consult (spawn_savi_status, spawn_status, spawn_team_status, spawn_latest).

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