opchain

Claude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
67%
命名品質
97%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~645Token(工具定義)
~604 B典型回應大小
中等的注意力影響(128k 上下文的 0.50%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "opchain-skills": {
      "url": "https://opchain.dev/mcp"
    }
  }
}

遠端端點

https://opchain.dev/mcpstreamable-http

它能做什麼

工具清單

工具(7)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢list_skills

List every opchain skill (id, displayName, description, phases, commands). Call this first to see the concept→ship pipeline.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
⚪route(query)

Map a request or an /oc-* command to the skill that should handle it, with the entry phase. Use when you're unsure which skill fits.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "An /oc-* command (e.g. /oc-discover) or a natural-language request (e.g. 'build me an app')."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}
🟢get_skill(id)

Return the full SKILL.md (the instructions) for one skill id. Load it, then follow it. Read get_orchestrator once before your first get_skill in a session.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Skill id, e.g. oc-app-architect."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢get_orchestrator

Return the shared orchestrator protocol (welcome flow, pipeline map, active-chaining rules). Read once at the start of a session.

輸入結構描述

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

Create a private server-issued session for checkpoint storage. Retain the returned sessionId and use it with read_checkpoint/write_checkpoint; never invent or share one.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟡read_checkpoint(skill, sessionId)

Read a skill's saved session checkpoint (where you left off). sessionId must be a private token returned by create_checkpoint_session.

輸入結構描述

{
  "type": "object",
  "properties": {
    "skill": {
      "type": "string"
    },
    "sessionId": {
      "type": "string",
      "minLength": 36,
      "maxLength": 128,
      "description": "Private token returned by create_checkpoint_session."
    }
  },
  "required": [
    "skill",
    "sessionId"
  ],
  "additionalProperties": false
}
🟡write_checkpoint(skill, sessionId, checkpoint, expectedRevision)

Persist a skill's session checkpoint so progress survives across sessions. Stores the object as given (any JSON object up to 64 KiB); it does not validate it against the opchain checkpoint protocol, so write the shape the protocol documents.

輸入結構描述

{
  "type": "object",
  "properties": {
    "skill": {
      "type": "string"
    },
    "sessionId": {
      "type": "string",
      "minLength": 36,
      "maxLength": 128,
      "description": "Private token returned by create_checkpoint_session."
    },
    "checkpoint": {
      "type": "object",
      "description": "The checkpoint JSON to store (skill_state, next_actions, etc.)."
    },
    "expectedRevision": {
      "oneOf": [
        {
          "type": "string",
          "minLength": 1
        },
        {
          "type": "null"
        }
      ],
      "description": "Local durable transport only: null creates only if absent; a revision updates only that revision. Omit for atomic unguarded replacement."
    }
  },
  "required": [
    "skill",
    "sessionId",
    "checkpoint"
  ],
  "additionalProperties": false
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本7 個工具
已驗證未記錄版本7 個工具
已驗證未記錄版本7 個工具