Robot Skill Hub

Search pinned robot code, compatibility and execution evidence. Prepare locally with the Hub CLI.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
64%
Naming quality
100%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~508Tokens (tool definitions)
~1.2 KBTypical response size
Minimal attention impact (0.40% 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": {
    "robot-skill-hub": {
      "url": "https://api.superfastrobotics.com/mcp"
    }
  }
}

Remote endpoints

https://api.superfastrobotics.com/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢find_robot_skills(q, runtime, runtime_version, robot, controller, ...)

Search pinned robot code across robots and runtimes. Results distinguish prepared recipes from upstream references; source discovery is not runtime verification.

Input Schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 240,
      "description": "All query terms must match word prefixes. Standalone A*, D* and RRT* are read as astar, dstar and rrtstar; embedded identifiers and repeated stars keep ordinary tokenization. Empty q browses."
    },
    "runtime": {
      "type": "string",
      "maxLength": 80
    },
    "runtime_version": {
      "type": "string",
      "maxLength": 80
    },
    "robot": {
      "type": "string",
      "maxLength": 80
    },
    "controller": {
      "type": "string",
      "maxLength": 80
    },
    "observation": {
      "type": "string",
      "maxLength": 80
    },
    "os": {
      "type": "string",
      "maxLength": 80
    },
    "python": {
      "type": "string",
      "maxLength": 80
    },
    "architecture": {
      "type": "string",
      "maxLength": 80
    },
    "kind": {
      "type": "string",
      "enum": [
        "preparation_recipe",
        "source_reference"
      ]
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "offset": {
      "type": "integer",
      "minimum": 0
    },
    "hub_commit": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
🟢inspect_robot_skill(skill_id, record_version)

Read a pinned recipe or reference, provenance, license, access instructions and exact evidence. No installation or execution is performed.

Input Schema

{
  "type": "object",
  "properties": {
    "skill_id": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
    },
    "record_version": {
      "type": "string",
      "maxLength": 120,
      "description": "Copy record_version from the selected search result. Source references use source-<source.sha256>, not record.maintenance.record_version."
    }
  },
  "required": [
    "skill_id"
  ],
  "additionalProperties": false
}
🟢get_hub_capabilities

Read public discovery, preparation, contribution and task-memory capabilities, local CLI onboarding links and current catalog counts. No authentication is needed for reads.

Input Schema

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

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools