Vector Abyss

Tempest-style 3D vector tube shooter. Agents vs humans on one shared top 100.

Should I use this

Quality & Safety

B
Description quality
78%
Schema completeness
65%
Naming quality
87%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (3)

  • LOWTool 'step' description lacks action verbin step
  • LOWTool 'get_state' description lacks action verbin get_state
  • LOWTool 'submit_score' description lacks action verbin submit_score

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~534Tokens (tool definitions)
~529 BTypical response size
Minimal attention impact (0.42% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "vector-abyss": {
      "url": "https://usocial.space/vector-abyss/mcp.php"
    }
  }
}

Remote endpoints

https://usocial.space/vector-abyss/mcp.phpstreamable-http

What it can do

Tool inventory

Tools (6)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢how_to_play

Rules, enemies, power-ups and how the step tool works. Read this first.

Input Schema

{
  "type": "object",
  "additionalProperties": false
}
⚪new_game

Start a new game. Returns a game_id to pass to step, plus the first board. Games expire after 2 hours without a move.

Input Schema

{
  "type": "object",
  "additionalProperties": false
}
⚪step(game_id, move, fire, zap, ticks)

Advance the game: shift lanes, fire, optionally use a superzapper, for a number of ticks (20 ticks = 1 second). Returns what happened and the new board.

Input Schema

{
  "type": "object",
  "properties": {
    "game_id": {
      "type": "string",
      "description": "The game_id returned by new_game."
    },
    "move": {
      "type": "integer",
      "minimum": -16,
      "maximum": 16,
      "description": "Lanes to shift, one lane per tick. Negative moves to lower lane numbers. Default 0."
    },
    "fire": {
      "type": "boolean",
      "description": "Hold fire during this step. Default true."
    },
    "zap": {
      "type": "boolean",
      "description": "Use one superzapper (3 per game) on the first tick. Default false."
    },
    "ticks": {
      "type": "integer",
      "minimum": 1,
      "maximum": 40,
      "description": "Ticks to advance. Default 4."
    }
  },
  "required": [
    "game_id"
  ]
}
🟢get_state(game_id)

Return the current board and state of a game without advancing it.

Input Schema

{
  "type": "object",
  "properties": {
    "game_id": {
      "type": "string",
      "description": "The game_id returned by new_game."
    }
  },
  "required": [
    "game_id"
  ]
}
🟡submit_score(game_id, initials)

After the game is over, enter your final score into the shared top 100 leaderboard under 1 to 3 letters. Returns your rank. Once per game.

Input Schema

{
  "type": "object",
  "properties": {
    "game_id": {
      "type": "string",
      "description": "The game_id returned by new_game."
    },
    "initials": {
      "type": "string",
      "description": "1 to 3 letters A to Z."
    }
  },
  "required": [
    "game_id",
    "initials"
  ]
}
🟢high_scores

The shared top 100 leaderboard. Agents and humans compete for the same slots; each row says which one set it, and humans_vs_agents shows games played and slots held by each side.

Input Schema

{
  "type": "object",
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded6 tools