planist-mcp
Enables AI clients to inspect, read, and propose page edits in Planist workspaces over MCP. Supports listing pages, fetching structured content, and submitting edit proposals for review.
README
<div align="center">
🔌 Planist-MCP
Model Context Protocol (MCP) Server for Planist APOS
Connect Claude, Cursor, and External AI Agents directly to your Planist Workspace.
<p align="center"> <em>An out-of-process, privacy-focused, Model Context Protocol server enabling AI models to inspect, read, and propose edits across Planist's 6 hyper-fused page types and reactive variable substrate.</em> </p>
</div>
🌟 Overview
Planist-MCP is the official Model Context Protocol server for Planist — the Agentic Project Operating System (APOS).
By isolating AI interactions into an out-of-process MCP server, Planist ensures maximum data security, zero in-process script execution vulnerabilities, and seamless compatibility with Claude Desktop, Cursor, and custom AI agent frameworks.
┌────────────────────────────────────────────────────────┐
│ External AI Ecosystem (Out-of-Process) │
│ │
│ [ Claude / LLM ] ──> [ Planist-MCP Server (TS) ] │
└───────────────────────────┬────────────────────────────┘
│ (JSON-RPC stdio / HTTP)
▼
┌────────────────────────────────────────────────────────┐
│ Planist Desktop Application (APOS) │
│ │
│ 1. Host-Local API Listener (127.0.0.1:8080) │
│ 2. AI Grant Validation & Proposal Review Panel │
│ 3. ProjectAuthority (Typed Transaction Write-Back) │
└────────────────────────────────────────────────────────┘
✨ Features & Capabilities
- 📄 Doc (
docs): Inspect Markdown block structures, append new sections, and propose document diffs (LivePageProposal). - 📊 Sheet (
sheet): Read/write specific cell ranges (A1:D20), evaluate formulas, and trigger data-driven chart projections. - 🖼️ Slide (
slide): Generate structural Markdown slides with rendering hints and speaker notes (Speaker Notes). - 🎨 Edgeless (
edgeless): Query spatial node cards, supply approximate node placements (letting Planist's internal engine layout the canvas), and draw vector ink strokes. - 📐 Design (
design): Query exact UI element trees, create vector frames with exact geometry(x, y, w, h), and export SVG previews. - 📈 Dashboard (
dashboard): Select components, bind metric data variables, and set up dynamic KPI dashboard grids. - ⚡ Reactive Variable Substrate: List, inspect, and update project-scoped reactive variables (
planist_update_variable), driving real-time updates across bound Sheets, Dashboards, and Docs!
🛠️ MCP Tools Specification
1. Workspace & Page Lifecycle Tools
| Tool Name | Parameters | Description |
|---|---|---|
planist_list_pages |
kindFilter? |
List accessible pages in the workspace (filtered by docs, sheet, slide, edgeless, design, dashboard). |
planist_read_page |
pageId |
Read the AST, Markdown, or structural block representation of a specific page by its Stable ID. |
planist_propose_page_edit |
pageId, summary, markdownContent |
Submit a structured page edit proposal (LivePageProposal) for human review in Planist. |
2. Reactive Project Variable Tools
| Tool Name | Parameters | Description |
|---|---|---|
planist_list_variables |
None | List all reactive typed variables in the Project Variable Substrate. |
planist_get_variable |
variableKey |
Fetch current value, type contract, and UI binding references for a variable. |
planist_update_variable |
variableKey, value, summary? |
Update a project variable value, driving automatic reactive UI updates across bound Sheet cells, Dashboard KPIs, and Docs (Execute ➔ Variable ➔ Plan loop). |
📦 Installation & Build
# Clone the repository
git clone https://github.com/MiuDog/planist-mcp.git
cd planist-mcp
# Install dependencies
npm install
# Build TypeScript code to dist/
npm run build
⚙️ Configuration & Setup
Integrating with Claude Desktop
Add the following to your claude_desktop_config.json (located at %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"planist-mcp": {
"command": "node",
"args": ["C:/Projects/planist-mcp/dist/index.js"],
"env": {
"PLANIST_API_HOST": "http://127.0.0.1:8080",
"PLANIST_GRANT_TOKEN": "<YOUR_LOCAL_GRANT_TOKEN>"
}
}
}
}
🔒 Security & Human-in-the-Loop Governance
- Out-of-Process Isolation: The MCP server runs outside Planist's main Flutter execution thread.
- Local Host Listener: API connections are strictly bound to
127.0.0.1(ADR-0029). - Human Approval: Edit proposals sent via
planist_propose_page_editmust be approved by human users in the Planist Review Panel unless authorized by an active AI Capability Grant (ADR-0034).
<div align="center">
Planist-MCP — Empowering Intelligent Collaboration for Planist.
Planist Core Repository • MCP Protocol Docs
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器