covagashi

Eplan RAG MCP — AI skill for Claude Code

AI community

EPLAN Electric P8 2026 + AI: MCP servers, docs RAG, and a Claude Code skill for EPLAN scripting/API development.

How to install Eplan RAG MCP

This entry records only its repository, not the path inside it, so there is no exact command to give. Open covagashi/eplan-rag-mcp and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Eplan RAG MCP does

EPLAN Electric P8 2026 + AI: MCP servers, docs RAG, and a Claude Code skill for EPLAN scripting/API development. EEC PRO RAG

Alternatives in AI

MCP Use — The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents 9.5k ★
Rulesync — by dyoshikawa - A Node.js CLI tool that automatically generates configs (rules, ignore files, MCP servers, com 909 ★
Wax — Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S 791 ★

README

**Status: actively developed, tools work.** The MCP server itself is reliable — every action runs and has been exercised live. What's still being sharpened is *context*: an LLM with 180+ low-level tools and no guidance will guess wrong action names or parameters. Point it at the [`eplan-development` skill](#claude-code-skill-for-eplan-development) and the [docs RAGs](#remote-documentation-rags-p8-eec-pro-and-2027) before asking it to do anything non-trivial, and give it a clear, planned task rather than an open-ended one. Bug reports and PRs that improve tool docstrings, the skill, or RAG coverage are very welcome.

EPLAN AI Automation Toolkit

**English** | [中文](#eplan-ai-自动化工具包)

A collection of AI-assisted automation tools for **EPLAN Electric P8** and **EPLAN EEC Pro 2026**, built around the Model Context Protocol (MCP).

The repo contains three independent sub-projects: a local MCP server that drives EPLAN P8 directly, and two remote MCP servers hosted on Cloudflare Workers that expose the indexed documentation via semantic search.

Working with an LLM here? Read [`llm.md`](llm.md) — it explains, in LLM-facing terms, everything the toolkit can do and configure.

Repository Layout

.
├── eplan-p8-mcp-server/          # LOCAL: MCP server that controls EPLAN P8
├── cloudflare-rag-eplan-p8/      # REMOTE: Cloudflare Worker that serves the P8 docs RAG over MCP
├── cloudflare-rag-eecpro/        # REMOTE: Cloudflare Worker that serves the EEC Pro docs RAG over MCP
└── claude-skills/                # SKILL: Claude Code skill for EPLAN P8 development

Folder	Type	Purpose	EPLAN product
`eplan-p8-mcp-server/`	Local Python MCP	Drive a running EPLAN instance from Claude (open/close projects, exports, reports, scripts, etc.)	EPLAN Electric P8
`cloudflare-rag-eplan-p8/`	Remote Cloudflare Worker	Serve the P8 doc index as a remote MCP + REST API	EPLAN Electric P8
`clou