What environments does Markdown Rules require?
Node.js v18 or higher and an MCP‑supported AI coding tool like Cursor.
@valstro
基本情報
The portable alternative to Cursor Rules and IDE-specific rules.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"markdown-rules-mcp": {
"command": "npx",
"args": [
"-y",
"@valstro/markdown-rules-mcp"
],
"env": {
"PROJECT_ROOT": "/absolute/path/to/project/root",
"MARKDOWN_INCLUDE": "./docs/**/*.md",
"HOIST_CONTEXT": true
}
}
}
}Get relevant markdown docs inside this project before answering the user's query to help you reply based on more context. # Usage Instructions ## When to use "get_relevant_docs" tool * You **must** call the "get_relevant_docs" MCP tool before providing your first response in any new chat session. * After the initial call in a chat, you should **only** call "get_relevant_docs" again if one of these specific situations occurs: * The user explicitly requests it. * The user attaches new files. * The user's query introduces a completely new topic unrelated to the previous discussion. ## How to use "get_relevant_docs" tool * "attachedFiles": ALWAYS include file paths the user has attached in their query. * "projectDocs" * ONLY include project docs that are VERY RELEVANT to user's query. * You must have a high confidence when picking docs that may be relevant. * If the user's query is a generic question unrelated to this specific project, leave this empty. * Always heavily bias towards leaving this empty.
Reindex the docs. Useful for when you want to force a re-index of the docs because there were changes to the docs or the index
Print a full count & summary of the docs in the index. Also shows the usage instructions for the `get_relevant_docs` tool. Useful for debugging. Will only show the first 20 docs in each category & a small preview of the content.
Markdown Rules is an MCP server that organizes project documentation into structured context for AI coding tools like Cursor. It uses YAML frontmatter in Markdown files to define how each document is included in AI conversations.
Install globally with npm install -g @valstro/markdown-rules-mcp, then configure the MCP server with PROJECT_ROOT, MARKDOWN_INCLUDE, and optional HOIST_CONTEXT environment variables. Create .md files with YAML frontmatter and invoke get_relevant_docs to fetch relevant documentation.
.ts files are added)@ symbol for ad‑hoc needsNode.js v18 or higher and an MCP‑supported AI coding tool like Cursor.
Via YAML frontmatter: `alwaysApply: true` for global, `globs` list for auto‑attached, a `description` for agent‑requested, or no frontmatter for manual inclusion.
Yes. Create a `markdown-rules.md` file in your project root. The path can also be customized via the `USAGE_INSTRUCTIONS_PATH` environment variable.
Yes. Append `?md-link=true` to include the full file, or `?md-embed=START-END` to embed specific line ranges inline.
By default, Markdown Rules excludes `**/node_modules/**,**/build/**,**/dist/**,**/.git/**,**/coverage/**,**/.next/**,**/.nuxt/**,**/out/**,**/.cache/**,**/tmp/**,**/temp/**`.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
コメント