Layerz

io.github.layerzlabs由 GitHub 账号 layerzlabs 发布v0.5.2更新于 Nov 5, 2026

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

已验证Streamable HTTP可网页运行效率与工作流金融数据与分析

概览

AI 生成的概览

Layerz 的托管 MCP 服务器：面向结构化财务建模表格，让助手构建、编辑、版本管理模型并导出 Excel。

可以做什么
  • 查找和读取模型，查看依赖关系并校验模型结构
  • 从蓝图或模板创建模型，修补条目并匹配条目
  • 设置建模约定、FINANCE.md 与自定义助手指令
  • 管理情景、分支、实际数与交易记录
  • 导入文件与数据源，管理集成与映射
  • 查看版本历史与差异，共享模型并导出 Excel
适用场景
适合让助手构建或维护带真实公式与依赖关系的财务模型，而不是零散的表格单元格，并能在后续会话中继续编辑。也适合需要把助手生成的模型导出为干净 Excel 文件的团队。
运行要求
远程 streamable HTTP 端点 layerz.cc/mcp，无需本地安装。需要 Layerz 账号并通过 OAuth 2.1（PKCE、动态客户端注册）登录；不支持 OAuth 的客户端可用 Layerz API 密钥作为 bearer token。需要网络访问。
安装前请注意
服务器会修改和删除模型数据：可删除分支、共享模型、管理版本，批准前应核对变更。财务数据与约定会存放在第三方托管服务中。当第二个人编辑同一批模型时需要付费方案。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Layerz，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.layerzlabs%2Flayerz/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "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.

来源：README.md，提交 5813a3c

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

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

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分