MCP MeasureMCP Measure

索引已观测

Wever World Data

Discover Wever services, process data, and delegate checked results between agents.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
83%
命名质量
96%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~2,007token 数（工具定义）
~1.6 KB典型响应大小
对注意力有中等影响（占 128k 上下文窗口的 1.57%）

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中：

{
  "mcpServers": {
    "world-data": {
      "url": "https://wever-world-data.quiet-salad-e96e.workers.dev/mcp"
    }
  }
}

远程端点

https://wever-world-data.quiet-salad-e96e.workers.dev/mcpstreamable-http

它能做什么

工具清单

工具（10）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟡create_result_reference(job_id, recipient_client_id, request_key, ttl_seconds)

Authorize one recipient client_id to read one owned result with its own credential. Returns a credential-free, expiring reference for agent handoff. Owner access stays in the configured header. Requires explicit intended recipient; no permission to other jobs, deletion or resharing.

输入模式

{
  "type": "object",
  "properties": {
    "job_id": {
      "pattern": "^job_[a-f0-9]{32}$",
      "type": "string"
    },
    "recipient_client_id": {
      "description": "Public client identifier provided by the intended recipient through an authorized connection. Never their token.",
      "pattern": "^client_[a-f0-9]{24}$",
      "type": "string"
    },
    "request_key": {
      "description": "Stable reference idempotency key. Reuse with identical job, recipient and requested lifetime.",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.-]{0,79}$",
      "type": "string"
    },
    "ttl_seconds": {
      "default": 900,
      "description": "Reference lifetime, also bounded by the job and both access credentials' expiry.",
      "maximum": 3600,
      "minimum": 1,
      "type": "integer"
    }
  },
  "required": [
    "recipient_client_id",
    "job_id",
    "request_key"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🔴delete_job(job_id)

Delete the owner's stored result content. Retains an idempotency tombstone until expiry and does not reset quotas. Configure the owner's bearer access header.

输入模式

{
  "type": "object",
  "properties": {
    "job_id": {
      "pattern": "^job_[a-f0-9]{32}$",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢get_catalog

Read public capabilities, free allowances, access bootstrap, privacy, retention and HTTP discovery routes. No access credential required.

输入模式

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

输出模式

{
  "type": "object"
}
🟢get_job(job_id)

Recover the original complete private CSV or audit result using its job_id and the owner's bearer access header. Results expire within 24 hours and cannot outlive access.

输入模式

{
  "type": "object",
  "properties": {
    "job_id": {
      "pattern": "^job_[a-f0-9]{32}$",
      "type": "string"
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢get_result_reference(reference_id)

Retrieve the full shared result using the nominated recipient's configured bearer header. The reference alone grants no access. Expired, revoked or deleted results are unavailable.

输入模式

{
  "type": "object",
  "properties": {
    "reference_id": {
      "pattern": "^ref_[a-f0-9]{32}$",
      "type": "string"
    }
  },
  "required": [
    "reference_id"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢resolve_capability(service_id)

Resolve an exact canonical Wever service_id to its maintained connection metadata, contract, limits and access steps. Unknown identities are rejected; no caller-supplied URL is fetched. Does not verify live availability or authorize execution.

输入模式

{
  "type": "object",
  "properties": {
    "service_id": {
      "description": "Exact canonical service_id from capability search, at most 96 UTF-8 bytes. Never a URL or credential.",
      "maxLength": 96,
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "service_id"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🔴revoke_result_reference(reference_id)

Owner revokes future retrieval through one shared result reference. Repeating this action is safe; previously downloaded copies cannot be recalled.

输入模式

{
  "type": "object",
  "properties": {
    "reference_id": {
      "pattern": "^ref_[a-f0-9]{32}$",
      "type": "string"
    }
  },
  "required": [
    "reference_id"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟢search_capabilities(limit, query)

Find maintained Wever capabilities by a short task description or keyword. Returns fixed known services with connection details, contracts, limits and access steps. Does not execute work, grant permissions, search the whole web, or verify live availability.

输入模式

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 5,
      "maximum": 5,
      "minimum": 1,
      "type": "integer"
    },
    "query": {
      "description": "Nonblank query of at most 160 UTF-8 bytes. Deterministic keyword matching over maintained Wever services only.",
      "maxLength": 160,
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}
🟡submit_audit(csv_text, expected_records, request_key, requested_rules, rule, ...)

Audit bounded CSV against caller-supplied expected records with explicit grouping, exact source references, lineage and integrity checks. A completed audit can report mismatches or blocked parsing. Inspect result.status, comparison, ambiguities and unsupported rules. No factual verification or inferred transformations.

输入模式

{
  "type": "object",
  "properties": {
    "csv_text": {
      "description": "At most 8192 UTF-8 bytes, 20 data records, 30 columns and 4096 UTF-8 bytes per cell. Exact strings are preserved.",
      "maxLength": 8192,
      "type": "string"
    },
    "expected_records": {
      "description": "Ordered expected records; field names and values are strings of at most 4096 UTF-8 bytes each.",
      "items": {
        "additionalProperties": {
          "maxLength": 4096,
          "type": "string"
        },
        "maxProperties": 30,
        "propertyNames": {
          "maxLength": 4096
        },
        "type": "object"
      },
      "maxItems": 20,
      "type": "array"
    },
    "request_key": {
      "description": "Stable idempotency key shared across CSV and audit. Reuse only with identical input for the same capability.",
      "maxLength": 80,
      "minLength": 1,
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.-]{0,79}$",
      "type": "string"
    },
    "requested_rules": {
      "description": "Descriptive requests, each at most 200 UTF-8 bytes. Every entry is reported unsupported; these do not authorize extra transformations.",
      "items": {
        "maxLength": 200,
        "type": "string"
      },
      "maxItems": 20,
      "type": "array"
    },
    "rule": {
      "default": {
        "kind": "preserve_rows"
      },
      "description": "Supports {kind: preserve_rows} or {kind: explicit_groups, groups: [{source_records: [1,2], concatenate: {column: separator}}]}. Source indexes are one-based and exclude the header. Invalid or unsupported rule options are findings with preserving fallback. No grouping is inferred. At most 8192 UTF-8 bytes.",
      "type": "object"
    },
    "source_metadata": {
      "additionalProperties": false,
      "description": "Descriptive metadata only, each value at most 200 UTF-8 bytes. No URL fetching or encoding conversion.",
      "properties": {
        "encoding": {
          "maxLength": 200,
          "type": "string"
        },
        "provider": {
          "maxLength": 200,
          "type": "string"
        },
        "version": {
          "maxLength": 200,
          "type": "string"
        }
      },
      "type": "object"
    }
  },
  "required": [
    "csv_text",
    "expected_records",
    "request_key"
  ],
  "additionalProperties": false,
  "description": "Complete canonical UTF-8 JSON payload at most 32768 bytes, HTTP body at most 48 KiB, nesting at most 32. The complete stored job envelope must fit 256 KiB or the request fails without storing a partial report."
}

输出模式

{
  "type": "object"
}
🟡submit_csv(csv_text, request_key, schema)

Normalize bounded CSV using explicit column rules. Returns a complete private job and checked CSV. Configure bearer access in the client header. Reuse request_key on retries.

输入模式

{
  "type": "object",
  "properties": {
    "csv_text": {
      "description": "At most 16 KiB UTF-8 and 100 data records",
      "maxLength": 16384,
      "type": "string"
    },
    "request_key": {
      "description": "Stable idempotency key shared across CSV and audit. Reuse only with identical input for the same capability.",
      "maxLength": 80,
      "minLength": 1,
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.-]{0,79}$",
      "type": "string"
    },
    "schema": {
      "additionalProperties": false,
      "properties": {
        "columns": {
          "items": {
            "additionalProperties": false,
            "properties": {
              "case": {
                "enum": [
                  "preserve",
                  "upper",
                  "lower"
                ],
                "type": "string"
              },
              "name": {
                "pattern": "^[A-Za-z][A-Za-z0-9_]{0,63}$",
                "type": "string"
              },
              "required": {
                "default": false,
                "type": "boolean"
              },
              "scale": {
                "description": "A finite JSON number with an integral value from 0 through 6. Numeric 2 and 2.0 are accepted and normalize to the same integer scale. Fractions, booleans, strings and nonfinite numbers are rejected.",
                "maximum": 6,
                "minimum": 0,
                "type": "integer"
              },
              "source": {
                "maxLength": 128,
                "minLength": 1,
                "type": "string"
              },
              "type": {
                "default": "text",
                "enum": [
                  "text",
                  "integer",
                  "decimal"
                ],
                "type": "string"
              }
            },
            "required": [
              "name",
              "source"
            ],
            "type": "object"
          },
          "maxItems": 30,
          "minItems": 1,
          "type": "array"
        },
        "unique_by": {
          "items": {
            "type": "string"
          },
          "type": "array",
          "uniqueItems": true
        }
      },
      "required": [
        "columns"
      ],
      "type": "object"
    }
  },
  "required": [
    "csv_text",
    "schema",
    "request_key"
  ],
  "additionalProperties": false
}

输出模式

{
  "type": "object"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本10 个工具
已验证未记录版本10 个工具
已验证未记录版本10 个工具