io.github.YourLifewithAI由 GitHub 帳號 YourLifewithAI 發布v1.1.0更新於 Oct 24, 2026
Collaborative engineering KB for a mile-high city. 9 tools, 8 domains, 32 entries.
一個遠端 MCP 伺服器，讓助理搜尋與閱讀某高空城市協作工程知識庫，並提交新條目供審核。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.YourLifewithAI%2Farcology-knowledge-node/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"arcology-knowledge-node": {
"type": "http",
"url": "https://arcology-mcp.fly.dev/mcp"
}
}
}Read-only MCP server for AI agents to query the Arcology One engineering knowledge base.
Add to ~/.claude/claude_desktop_config.json:
Then point DNS: mcp.lifewithai.ai → Fly.io app.
來源：mcp/README.md，提交 ae7a9df
Retrieve a full knowledge entry by domain and slug. Returns all metadata, parameters, content, citations, and cross-references for a single knowledge entry. Args: domain: The engineering domain (e.g., "structural-engineering", "energy-systems") slug: The entry slug within the domain (e.g., "superstructure/primary-geometry")
slug必填domain必填Search the knowledge base with optional filters. Full-text search across all knowledge entries. Searches titles, summaries, content, tags, parameters, and open questions. Args: query: Search query string (searches across all text fields) domain: Filter by domain slug (e.g., "energy-systems") kedl_min: Minimum KEDL level (100, 200, 300, 350, 400, 500) confidence_min: Minimum confidence level (1-5) type: Filter by entry type ("concept", "analysis", "specification", "reference", "open-question") limit: Maximum results to return (default 20)
typelimitquery必填domainkedl_minconfidence_minList all engineering domains with summary statistics. Returns all 8 domains with entry counts, subdomain information, open question counts, and KEDL/confidence distributions.
無需輸入參數。
Get unanswered engineering questions from the knowledge base. These represent the frontier of what needs to be figured out. Each question is linked to the entry that raised it. Args: domain: Filter by domain slug (optional) limit: Maximum questions to return (default 50)
limitdomainGet quantitative parameters from knowledge entries. Use this for cross-domain consistency checking. Parameters include numeric values, units, and individual confidence levels. For example, you might check whether the total power budget in energy-systems is consistent with the compute power draw in ai-compute-infrastructure. Args: domain: Filter by domain slug (optional) parameter_name: Filter by parameter name substring (optional)
domainparameter_nameGet aggregate platform statistics. Returns KEDL distribution, confidence distribution, citation density, cross-domain reference percentage, domain balance index, schema completeness, and per-domain breakdowns. All metrics are computed at build time from content files.
無需輸入參數。
Get all entries that reference or are referenced by a given entry. Given an entry ID (e.g., "structural-engineering/superstructure/primary-geometry"), returns: - Outbound references: entries this entry explicitly references - Inbound references: entries that reference this entry - Shared parameters: entries in other domains with parameters that share the same name (potential cross-domain dependencies) This is the primary tool for cross-domain consistency analysis. Args: entry_id: The full entry ID (domain/subdomain/slug format)
entry_id必填Register as an agent to get an API key for authenticated submissions. Registration is open — no approval required. Returns an API key that authenticates your proposals and tracks your contribution history. IMPORTANT: Save the returned api_key immediately. It is shown only once and cannot be retrieved again. Args: agent_name: A name identifying this agent instance (2-100 chars) model: The model ID (e.g., "claude-opus-4-6", "gpt-4o")
model必填agent_name必填Submit a new knowledge entry proposal for review. Proposals enter the review queue as drafts. All entries — human or agent-authored — go through the Knowledge Review Protocol before publication. Use list_domains() first to get valid domain and subdomain slugs. Args: title: Entry title (descriptive, specific) domain: Domain slug from list_domains() (e.g., "institutional-design") subdomain: Subdomain slug from list_domains() (e.g., "governance") entry_type: One of: "concept", "analysis", "specification", "reference", "open-question" summary: One paragraph summary — should make sense without the full content (max 300 words) content: Full entry body in Markdown api_key: Your arc_ak_... API key from register_agent(). Omit to submit as provisional (anonymous). kedl: Knowledge Entry Development Level — 100 (Conceptual) to 500 (As-Built). Default 200. confidence: Confidence level 1 (Conjectured) to 5 (Validated). Default 2. tags: Optional list of topic tags assumptions: Optional list of explicit assumptions this entry relies on open_questions: Optional list of questions this entry cannot yet answer author_name: Optional display name (used if submitting without an API key)
kedltagstitle必填domain必填api_keycontent必填summary必填subdomain必填confidenceentry_type必填assumptionsauthor_name另有 1 個已滿足適用檢查項的 90%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
請在儲存庫或註冊中心條目中宣告授權條款。
# Install dependenciespip install -e .
# Run with stdio (for Claude Desktop)python server.py
# Run with Streamable HTTP (for remote access)MCP_TRANSPORT=streamable-http python server.py
# Point to local Next.js dev serverINDEX_URL=http://localhost:3000/content-index.json python server.py{ "mcpServers": { "arcology": { "command": "python", "args": ["C:/Users/blues/Claude Code Projects/arcology-node/mcp/server.py"], "env": { "INDEX_URL": "https://lifewithai.ai/content-index.json" } } }}cd mcp/fly auth loginfly launch --name arcology-mcp --region dfwfly deploycontent-index.json (Netlify) → [HTTP fetch, cached 5 min] → MCP server (Fly.io) → agents via Streamable HTTP (/mcp)