planner-mcp
MCP server that turns planning documents into structured SQLite data and exposes plan metadata to AI agents, with tools to list and delete saved plans.
README
Planner MCP Monorepo
A TypeScript monorepo for turning planning documents into structured SQLite data and exposing plan metadata to AI agents through MCP.
Repository Map
| Path | Responsibility |
|---|---|
packages/api |
Markdown parser/formatter, domain types, SQLite repository, and REST API |
packages/mcp |
MCP stdio server and REST API client |
skills/idea-planner |
Phase-gated brain-dump planning skill and direct transfer scripts |
docs/REPOSITORY_MAP.md |
Detailed ownership, data flow, and extension map |
AGENTS.md |
Working rules and verification guidance for coding agents |
Requirements
- Node.js 22.5 or newer; SQLite is provided by Node's built-in
node:sqlitemodule - npm 10 or newer
curlfor the skill's shell scripts
Setup
npm install
npm run check
Run
Start the API in one terminal:
PLANNER_DB_PATH=planner.sqlite npm run dev:api
The API defaults to http://127.0.0.1:3000.
Start the MCP stdio server from an MCP client configuration:
{
"mcpServers": {
"planner": {
"command": "npm",
"args": ["run", "dev:mcp"],
"cwd": "/absolute/path/to/planner-mcp",
"env": {
"PLANNER_API_URL": "http://127.0.0.1:3000"
}
}
}
}
Example local use in opencode.json/opencode.jsonc
"mcp": {
"planner": {
"type": "local",
"enabled": true,
"command": ["npm", "run", "dev:mcp"],
"cwd": "/home/nhbody/git/planner-mcp",
"environment": {
"PLANNER_API_URL": "http://127.0.0.1:3000"
}
}
}
REST API
| Method | Endpoint | Behavior |
|---|---|---|
GET |
/health |
Readiness response |
PUT |
/plans |
Parse and add/update a Markdown plan; returns { "reference": "..." } |
GET |
/plans |
List plan frontmatter metadata |
GET |
/plans/:reference |
Reconstruct canonical Markdown |
DELETE |
/plans/:reference |
Delete a plan and all associated sections |
PUT /plans requires Content-Type: text/markdown. A frontmatter reference of New creates a UUID-backed PLAN-... reference. Any other reference updates that plan transactionally.
Direct Plan Transfer
The scripts stream files directly to and from the API to avoid duplicating plan content in an agent context:
skills/idea-planner/scripts/upload-plan.sh path/to/plan.md
skills/idea-planner/scripts/download-plan.sh PLAN-id path/to/plan.md
skills/idea-planner/scripts/sync-plan.sh path/to/plan.md
Set PLANNER_API_URL to override the default API URL. sync-plan.sh uploads, captures the reference, and atomically replaces the local document with canonical Markdown containing that reference.
MCP Surface
The MCP server exposes list_plans, which returns saved plans and metadata, and delete_plan, which permanently deletes a plan and its associated sections. delete_plan is destructive and must only be invoked after an explicit user request to delete that plan. Use the shell scripts for bulk Markdown upload and download.
Verification
npm run typecheck
npm run test:unit
npm run test:integration
npm run test:e2e
npm run build
npm run check
Tests use in-memory or temporary SQLite databases and do not touch planner.sqlite.
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.