Is the Openmark MCP server down?

• Added readOnlyHint: true (inferred from the name). (verify)

{
  "name": "estimate_cost",
  "description": "Credits a run_benchmark call would use, before spending anything: the expected total, the split per model, the balance needed to start, the worst case, and the user's balance. Same inputs and run settings as run_benchmark. Use it to drop an expensive model, or to compare settings (e.g. max_tokens), before running.",
  "inputSchema": {
    "type": "object",
    "required": [
      "task_yaml",
      "models"
    ],
    "properties": {
      "models": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "maxItems": 20,
        "minItems": 1
      },
      "preset": {
        "enum": [
          "standard",
          "thorough"
        ],
        "type": "string",
        "description": "Like the app's presets: standard = 2 passes + snappy timeouts (the default), thorough = 3 passes + patient timeouts. Explicit stability_runs / timeout_profile override it"
      },
      "fail_fast": {
        "type": "boolean",
        "default": true,
        "description": "Stop a model after repeated errors to save credits. Set false to let every model finish, e.g. to diagnose failures"
      },
      "task_yaml": {
        "type": "string",
        "description": "The full task YAML (a JSON object with the same fields also works)"
      },
      "max_tokens": {
        "type": "integer",
        "default": 500,
        "maximum": 16000,
        "minimum": 0,
        "description": "Output token limit per answer, 16 to 16000; 0 = no limit. Keep the default unless results show it was too low: a higher limit raises the credits needed to start. get_results flags models whose answers came back empty or near the limit; re-run those with a higher value"
      },
      "upload_uid": {
        "type": "string",
        "description": "From prepare_attachments, so image and document tokens are counted"
      },
      "custom_timeout": {
        "type": "integer",
        "maximum": 600,
        "minimum": 120,
        "description": "Seconds per answer, with timeout_profile custom"
      },
      "stability_runs": {
        "type": "integer",
        "default": 2,
        "maximum": 5,
        "minimum": 1,
        "description": "Passes per model; 2+ shows which models are consistent"
      },
      "temp_preference": {
        "enum": [
          "low",
          "high"
        ],
        "type": "string",
        "default": "low",
        "description": "With temperature_discovery: which temperature wins a tie"
      },
      "timeout_profile": {
        "enum": [
          "snappy",
          "patient",
          "custom"
        ],
        "type": "string",
        "default": "snappy",
        "description": "How long to wait per answer: snappy 45s, patient 90s, custom = custom_timeout"
      },
      "temperature_discovery": {
        "type": "boolean",
        "default": false,
        "description": "Find each model's best temperature for this task. Costs about 6x as much"
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  },
  "title": "Estimate a run's cost"
}

• Added readOnlyHint: true (inferred from the name). (verify)

{
  "name": "get_account",
  "description": "The user's plan, credit balance and limits, and what a credit pack, Pro or Expert would unlock. Use it before large runs, or when a run is refused for credits or limits.",
  "inputSchema": {
    "type": "object",
    "properties": {}
  },
  "annotations": {
    "readOnlyHint": true
  },
  "title": "Account, credits and plans"
}

• Added readOnlyHint: true (inferred from the name). (verify)

{
  "name": "get_results",
  "description": "Status of a benchmark job, and once completed the ranked results (score, stability, cost per run, latency), the tests each model missed with its answer, a recommendation for the chosen objective and quick picks for the others.",
  "inputSchema": {
    "type": "object",
    "required": [
      "job_id"
    ],
    "properties": {
      "job_id": {
        "type": "string"
      },
      "tolerance": {
        "type": "number",
        "default": 2,
        "maximum": 50,
        "minimum": 0,
        "description": "Score points below the top score that still count as good enough"
      },
      "show_misses": {
        "type": "boolean",
        "default": true,
        "description": "List the tests each model got wrong, with the expected answer and the model's reply"
      },
      "optimize_for": {
        "enum": [
          "accuracy",
          "cost",
          "speed",
          "stability"
        ],
        "type": "string",
        "default": "accuracy",
        "description": "accuracy (same order as the app's results table): best score, then cheapest, then fastest. cost / speed / stability: cheapest / fastest / most consistent model within `tolerance` points of the top score"
      }
    }
  },
  "annotations": {
    "readOnlyHint": true
  },
  "title": "Get benchmark results"
}