MCP MeasureMCP Measure

index observed

agiscorecard-web3-compute

Compare GPU workload costs per accepted output, including setup, storage, egress and failed work.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
87%
Naming quality
93%
Poisoning risk
100%
Permission match
90%
Protocol compliance
100%

Findings (1)

  • LOWTool 'fetch' suggests web access but openWorldHint=falsein fetch

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~1,510Tokens (tool definitions)
~5.5 KBTypical response size
Moderate attention impact (1.18% 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": {
    "agiscorecard-web3-compute": {
      "url": "https://compute.agiscorecard.com/mcp"
    }
  }
}

Remote endpoints

https://compute.agiscorecard.com/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢search(query)

Search this server’s public AI/Web3 tools and citation pages. English and Chinese names supported. Empty query lists the available worksheets.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 160
    }
  },
  "required": [
    "query"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "title": {
            "type": "string"
          },
          "url": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "title",
          "url"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "results"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢fetch(id)

Retrieve a public tool reference by the ID returned from search. Contains methodology, limits, official source links and fictional worked examples; no user records. Cite the returned canonical URL.

Input Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "enum": [
        "compute"
      ]
    }
  },
  "required": [
    "id"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "title": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "url": {
      "type": "string"
    },
    "metadata": {
      "type": "object",
      "properties": {
        "version": {
          "type": "string"
        },
        "revision": {
          "type": "string"
        },
        "reviewedAt": {
          "type": "string"
        },
        "evidenceType": {
          "type": "string"
        }
      },
      "required": [
        "version",
        "revision",
        "reviewedAt",
        "evidenceType"
      ],
      "additionalProperties": false
    }
  },
  "required": [
    "id",
    "title",
    "text",
    "url",
    "metadata"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢compare_compute_costs(workload, model, currency, minimumPassRate, runs)

Compute Lens compares measured workload runs using total entered compute, setup, storage and egress costs per accepted output. It filters mismatched workload labels, currencies, quality and memory limits. All examples are fictional; no live GPU quotes are supplied. No live GPU inventory, automatic benchmarking, reservation, infrastructure management or verified savings. Retrieve compute with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.

Input Schema

{
  "type": "object",
  "properties": {
    "workload": {
      "type": "string",
      "maxLength": 131072,
      "description": "Workload (preserve source text; decimal amounts must stay strings)"
    },
    "model": {
      "type": "string",
      "maxLength": 131072,
      "description": "Model (preserve source text; decimal amounts must stay strings)"
    },
    "currency": {
      "type": "string",
      "maxLength": 131072,
      "description": "Currency (preserve source text; decimal amounts must stay strings)"
    },
    "minimumPassRate": {
      "type": "number",
      "description": "Minimum accepted fraction (0–1)"
    },
    "runs": {
      "maxItems": 200,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "maxLength": 131072,
            "description": "Record ID (preserve source text; decimal amounts must stay strings)"
          },
          "provider": {
            "type": "string",
            "maxLength": 131072,
            "description": "Provider (preserve source text; decimal amounts must stay strings)"
          },
          "workload": {
            "type": "string",
            "maxLength": 131072,
            "description": "Workload (preserve source text; decimal amounts must stay strings)"
          },
          "model": {
            "type": "string",
            "maxLength": 131072,
            "description": "Model (preserve source text; decimal amounts must stay strings)"
          },
          "currency": {
            "type": "string",
            "maxLength": 131072,
            "description": "Currency (preserve source text; decimal amounts must stay strings)"
          },
          "hourlyCost": {
            "type": "string",
            "maxLength": 131072,
            "description": "Hourly compute rate (preserve source text; decimal amounts must stay strings)"
          },
          "setupSeconds": {
            "type": "number",
            "description": "Setup Seconds"
          },
          "runSeconds": {
            "type": "number",
            "description": "Run Seconds"
          },
          "storageCost": {
            "type": "string",
            "maxLength": 131072,
            "description": "Storage Cost (preserve source text; decimal amounts must stay strings)"
          },
          "egressCost": {
            "type": "string",
            "maxLength": 131072,
            "description": "Egress Cost (preserve source text; decimal amounts must stay strings)"
          },
          "accepted": {
            "type": "number",
            "description": "Accepted"
          },
          "attempts": {
            "type": "number",
            "description": "Attempts"
          },
          "memoryGB": {
            "type": "number",
            "description": "Required memory (GB)"
          },
          "availableMemoryGB": {
            "type": "number",
            "description": "Available memory (GB)"
          }
        },
        "required": [
          "id",
          "provider",
          "workload",
          "model",
          "currency",
          "hourlyCost",
          "setupSeconds",
          "runSeconds",
          "storageCost",
          "egressCost",
          "accepted",
          "attempts",
          "memoryGB",
          "availableMemoryGB"
        ],
        "additionalProperties": false,
        "description": "Exact record structure; the engine additionally checks bounds, dates, identifiers and cross-field constraints."
      },
      "description": "Runs"
    }
  },
  "required": [
    "workload",
    "model",
    "currency",
    "minimumPassRate",
    "runs"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false,
  "description": "Exact record structure; the engine additionally checks bounds, dates, identifiers and cross-field constraints."
}

Output Schema

{
  "type": "object",
  "properties": {
    "toolId": {
      "type": "string"
    },
    "version": {
      "type": "string"
    },
    "revision": {
      "type": "string"
    },
    "processing": {
      "type": "string"
    },
    "evidenceStatus": {
      "type": "string"
    },
    "citation": {
      "type": "object",
      "properties": {
        "title": {
          "type": "string"
        },
        "url": {
          "type": "string"
        },
        "methodUrl": {
          "type": "string"
        },
        "reviewedAt": {
          "type": "string"
        },
        "scope": {
          "type": "string"
        }
      },
      "required": [
        "title",
        "url",
        "methodUrl",
        "reviewedAt",
        "scope"
      ],
      "additionalProperties": false
    },
    "officialReferences": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "title": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "relationship": {
            "type": "string"
          }
        },
        "required": [
          "title",
          "url",
          "relationship"
        ],
        "additionalProperties": false
      }
    },
    "limitations": {
      "type": "string"
    },
    "report": {
      "type": "object",
      "properties": {
        "version": {
          "type": "string"
        },
        "title": {
          "type": "string"
        },
        "summary": {
          "type": "string"
        },
        "metrics": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "label": {
                "type": "string"
              },
              "value": {
                "type": [
                  "string",
                  "number"
                ]
              }
            },
            "required": [
              "label",
              "value"
            ],
            "additionalProperties": false
          }
        },
        "tables": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "title": {
                "type": "string"
              },
              "columns": {
                "type": "array",
                "items": {
                  "type": "string"
                }
              },
              "rows": {
                "type": "array",
                "items": {
                  "type": "array",
                  "items": {
                    "type": [
                      "string",
                      "number",
                      "boolean",
                      "null"
                    ]
                  }
                }
              }
            },
            "required": [
              "title",
              "columns",
              "rows"
            ],
            "additionalProperties": false
          }
        },
        "notes": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "data": {}
      },
      "required": [
        "version",
        "title",
        "summary",
        "metrics",
        "tables",
        "notes",
        "data"
      ],
      "additionalProperties": false
    }
  },
  "required": [
    "toolId",
    "version",
    "revision",
    "processing",
    "evidenceStatus",
    "citation",
    "officialReferences",
    "limitations",
    "report"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools