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">
š 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>
š Overview
Planist-MCP is the official Model Context Protocol server for Planist ā 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.
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā External AI Ecosystem (Out-of-Process) ā
ā ā
ā [ Claude / LLM ] āā> [ Planist-MCP Server (TS) ] ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāā¬āāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā (JSON-RPC stdio / HTTP)
ā¼
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Planist Desktop Application (APOS) ā
ā ā
ā 1. Host-Local API Listener (127.0.0.1:8080) ā
ā 2. AI Grant Validation & Proposal Review Panel ā
ā 3. ProjectAuthority (Typed Transaction Write-Back) ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
⨠Features & Capabilities
- š Doc (
docs): Inspect Markdown block structures, append new sections, and propose document diffs (LivePageProposal). - š Sheet (
sheet): Read/write specific cell ranges (A1:D20), evaluate formulas, and trigger data-driven chart projections. - š¼ļø Slide (
slide): Generate structural Markdown slides with rendering hints and speaker notes (Speaker Notes). - šØ Edgeless (
edgeless): Query spatial node cards, supply approximate node placements (letting Planist's internal engine layout the canvas), and draw vector ink strokes. - š Design (
design): Query exact UI element trees, create vector frames with exact geometry(x, y, w, h), and export SVG previews. - š Dashboard (
dashboard): Select components, bind metric data variables, and set up dynamic KPI dashboard grids. - ā” Reactive Variable Substrate: List, inspect, and update project-scoped reactive variables (
planist_update_variable), driving real-time updates across bound Sheets, Dashboards, and Docs!
š ļø 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 ā Variable ā Plan loop). |
š¦ 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
āļø 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>"
}
}
}
}
š 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 ā Empowering Intelligent Collaboration for Planist.
Planist Core Repository ⢠MCP Protocol Docs
</div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.