← WebMCP Directory

Tool tree

spencerheywood.com

Media & PersonalTools verified
Website
Hands-on AI transformation, enterprise automation, and production systems for complex industrial operations.
Explore capabilities
    get_live_lab_statsAnswer

    Fetch live stats for Spencer's self-hosted AI lab straight from his LLM gateway: decode throughput in tokens/sec (mean aggregate across concurrent streams, peak single-stream, 24-hour average), lifetime token and request totals, build cost vs hosted-API spend avoided, wall power draw, energy used, GPU utilization, the local-vs-api-overflow routing split, input-context lengths (median/p95 per request), and the top serving models. Use this whenever asked about the lab's performance or any of those numbers — never quote them from memory.

    View tool JSON
    {
      "name": "get_live_lab_stats",
      "kind": "answer",
      "impl": "imperative",
      "description": "Fetch live stats for Spencer's self-hosted AI lab straight from his LLM gateway: decode throughput in tokens/sec (mean aggregate across concurrent streams, peak single-stream, 24-hour average), lifetime token and request totals, build cost vs hosted-API spend avoided, wall power draw, energy used, GPU utilization, the local-vs-api-overflow routing split, input-context lengths (median/p95 per request), and the top serving models. Use this whenever asked about the lab's performance or any of those numbers — never quote them from memory.",
      "inputSchema": {
        "type": "object",
        "properties": {},
        "additionalProperties": false
      }
    }
    ask_local_modelAction

    Ask a question to the LLM running on Spencer's own hardware (served through his AgentGateway) and return its plain-text answer. Good for questions about his experience, projects, or AI lab that benefit from the model's own voice. Use sparingly — local generation takes several seconds.

    View tool JSON
    {
      "name": "ask_local_model",
      "kind": "act",
      "impl": "imperative",
      "description": "Ask a question to the LLM running on Spencer's own hardware (served through his AgentGateway) and return its plain-text answer. Good for questions about his experience, projects, or AI lab that benefit from the model's own voice. Use sparingly — local generation takes several seconds.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "question": {
            "type": "string",
            "description": "The question to ask the local model (max 600 characters)."
          }
        },
        "required": [
          "question"
        ],
        "additionalProperties": false
      }
    }
    navigate_to_sectionAction

    Scroll this page to one of its main sections so the user can see a specific part of Spencer's site.

    View tool JSON
    {
      "name": "navigate_to_section",
      "kind": "act",
      "impl": "imperative",
      "description": "Scroll this page to one of its main sections so the user can see a specific part of Spencer's site.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "section": {
            "type": "string",
            "enum": [
              "live-stats",
              "focus",
              "experience",
              "delivery-process",
              "ai-lab",
              "projects",
              "capabilities",
              "education",
              "contact"
            ],
            "description": "Which section to show."
          }
        },
        "required": [
          "section"
        ],
        "additionalProperties": false
      }
    }