Layerz

io.github.layerzlabs由 GitHub 帳號 layerzlabs 發布v0.5.2更新於 Nov 5, 2026

Financial models Claude builds and edits: items, formulas, dependencies, branches. Exports to Excel.

已驗證Streamable HTTP可網頁執行效率與工作流金融資料與分析

概覽

AI 產生的概覽

Layerz 的託管 MCP 伺服器：針對結構化財務建模試算表，讓助理建立、編輯、版本管理模型並匯出 Excel。

可以做什麼
  • 尋找與讀取模型，檢視相依關係並驗證模型結構
  • 從藍圖或範本建立模型，修補項目並比對項目
  • 設定建模慣例、FINANCE.md 與自訂助理指示
  • 管理情境、分支、實際數與交易紀錄
  • 匯入檔案與資料來源，管理整合與對應
  • 檢視版本歷程與差異，分享模型並匯出 Excel
適用情境
適合讓助理建立或維護具備真實公式與相依關係的財務模型，而非零散的試算表儲存格，並能在後續工作階段繼續編輯。也適合需要把助理產生的模型匯出成乾淨 Excel 檔案的團隊。
執行需求
遠端 streamable HTTP 端點 layerz.cc/mcp，無需在本機安裝。需要 Layerz 帳號並透過 OAuth 2.1（PKCE、動態用戶端註冊）登入；不支援 OAuth 的用戶端可用 Layerz API 金鑰作為 bearer token。需要網路存取。
安裝前請注意
伺服器會修改與刪除模型資料：可刪除分支、分享模型、管理版本，核准前應核對變更。財務資料與慣例會存放在第三方託管服務中。當第二個人編輯同一批模型時需要付費方案。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Layerz，將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

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。

交給代理程式安裝

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.layerzlabs%2Flayerz/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。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "layerz": {
      "type": "http",
      "url": "https://layerz.cc/mcp"
    }
  }
}

README

Layerz MCP

Financial models your AI agent builds and edits: items, formulas, dependencies, branches. Exports to Excel.

Layerz is a structured spreadsheet for financial models, ready for AI. This is its remote MCP server. Claude, ChatGPT, Codex or any MCP client works on the model structure itself, not on loose cells, so formulas hold when the agent changes an assumption and the model is still there next session.

[Layerz MCP connector]

The server is hosted. There is nothing to install or run locally: this repository holds the setup instructions and the metadata MCP directories read.

Why

Ask an AI to build a financial model and you get a workbook in 30 seconds. Then one assumption changes: links break, values get hardcoded, and the next session starts from scratch.

Layerz keeps the structure of a model (items, formulas with named references, the dependency graph, timelines) apart from its data (values, scenarios, actuals). The agent edits that structure through MCP tools, every change is versioned with a readable summary, and Excel is an export format: clean, standard .xlsx with live formulas, the file you send to people who never see the agent.

Setup

One click

ClientLink
Claude (claude.ai, desktop app, Cowork)layerz.cc/claude opens Settings → Connectors with Layerz pre-filled
ChatGPT and Codexlayerz.cc/chatgpt opens the Layerz plugin in the ChatGPT directory

Confirm, sign in to Layerz, done.

Cursor

[Add Layerz to Cursor]

Or add it to ~/.cursor/mcp.json:

json
{  "mcpServers": {    "layerz": { "url": "https://layerz.cc/mcp" }  }}

Cursor opens the Layerz sign-in the first time a tool is called.

By hand

Claude Code

bash
claude mcp add -t http layerz https://layerz.cc/mcp

Then run /mcp to authenticate in the browser.

OpenAI Codex

bash
codex mcp add layerz --url https://layerz.cc/mcpcodex mcp login layerz

Claude, without the link: Settings → Connectors → Add custom connector → https://layerz.cc/mcp

ChatGPT, without the directory: Settings → Security and login → Developer mode, then Plugins → + → https://layerz.cc/mcp

Mistral Le Chat: Settings → Connectors → Add custom MCP connector → https://layerz.cc/mcp

OpenCode: add to opencode.json, then run opencode mcp auth layerz

json
{  "$schema": "https://opencode.ai/config.json",  "mcp": {    "layerz": {      "type": "remote",      "url": "https://layerz.cc/mcp",      "oauth": {}    }  }}

Grok: grok.com/connectors → New Connector → Custom → https://layerz.cc/mcp

Antigravity CLI (formerly Gemini CLI): add to mcp_config.json

json
{  "mcpServers": {    "layerz": { "serverUrl": "https://layerz.cc/mcp" }  }}

Any other MCP client: point it at https://layerz.cc/mcp over streamable HTTP. Clients without OAuth can send a Layerz API key, created in the Layerz app, as a bearer token.

What the agent can do

29 tools, grouped by job. Read-only tools are annotated as such, so clients can run them without asking.

JobTools
Find and read modelslayerz_list_models, layerz_get_model, layerz_read, layerz_dependencies, layerz_validate_model
Build and editlayerz_create_model, layerz_build_from_blueprint, layerz_list_templates, layerz_patch, layerz_match_items
Conventionslayerz_get_conventions, layerz_set_finance_md, layerz_set_custom_instructions
Scenarios and actualslayerz_update_branch, layerz_delete_branch, layerz_import_branch, layerz_list_transactions
Import files and sourceslayerz_create_upload_url, layerz_parse_file, layerz_list_integrations, layerz_manage_integration, layerz_list_mappings, layerz_manage_mapping, layerz_external_ref
Versionslayerz_history, layerz_diff, layerz_manage_version
Share and exportlayerz_share_model, layerz_export

The server also exposes reference resources the agent reads on its own: modeling-guide://reference (session workflow, modeling patterns, validated patch examples), formula-spec://reference (the formula language) and format-spec://reference (number formats).

Using it well

The guidance lives on the server, so it is never out of date on your machine:

  • Conventions travel with the model. Each model carries a FINANCE.md (currency, units, sign convention, how the statements are built), and each workspace carries standing instructions for agents. The agent receives both when it opens a model.
  • The modeling guide comes from layerz_get_conventions { include_guide: true }. Agents read it at the start of a session.
  • Recipes (prompts for budgets, three-statement models, monthly closes, LBOs) are in the cookbook.

A good first prompt:

Build a three-statement model for a B2B SaaS company: 2 M€ ARR, 40 % growth, 18-month runway. Ask me what you need to know first.

Pricing

Free for one person working alone: unlimited models, MCP and REST API, Excel and JSON export. A paid plan starts when a second person edits the same models. Details at layerz.cc/pricing.

Related

  • finance-md: the open standard for financial conventions an agent reads
  • cookbook: recipes for financial work with AI agents
  • layerz.cc: the web app, where people review, share and collaborate on the same models

Versioning

One version, the server's. The number published to the official MCP Registry (io.github.layerzlabs/layerz, from the server.json of the Layerz code repo) is the only version; lhm.plugin.json and .cursor-plugin/plugin.json here mirror it, never one of their own. A change to this repository alone (a tool declared, a description reworded) ships under the current version. node scripts/check-version.mjs (run on every push and weekly) fails when the manifests disagree or run behind the registry, and only warns when a publish is pending.

Support

Questions or stuck on setup: [email protected]. Bugs and requests: open an issue in this repository.

License

The contents of this repository (documentation and metadata) are released under the MIT License. The Layerz server and web app are proprietary.

來源：README.md，提交 5813a3c

工具

0
該伺服器需要登入，因此 SourceWeft 無法在沒有帳號的情況下讀取其工具，也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

4
  1. v0.5.2最新Nov 5, 2026
  2. v0.5.1Nov 3, 2026
  3. v0.4.0Sep 30, 2026
  4. v0.3.0Sep 16, 2026

評分

已滿足適用檢查項的 85%

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。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分