mcp-me MCP Server | MCP Server List

Your AI assistants don't know who you are.Every time you start a conversation with Claude, Copilot, Cursor, or Windsurf, it's a blank slate — no context about your skills, your projects, your career, or what you care about.

mcp-me fixes that.It creates a structured personal profile that any AI assistant can read via theModel Context Protocol (MCP). Think of it as adigital identity layer for AI— your bio, career, skills, interests, projects, and more, always available to every AI tool you use.

You: "Write me a cover letter for this job" AI: (reads your me://career, me://skills, me://projects) "Based on your 5 years at Acme Corp, your TypeScript expertise, and your open-source work on mcp-me..."

- AI that knows you— Your assistants remember your skills, career, projects, and personality across every conversation
- Auto-generated— Pull data from 329 registered generators (implemented across 44 generator source files) with one command
- Privacy-first— All data stays local in YAML files on your machine. Nothing is sent to any cloud.
- Real-time plugins— 13 live integrations (Spotify now playing, GitHub repos, Last.fm scrobbles) that AI queries on demand
- Extensible— Community-driven generators and plugins. Add a new data source in ~10 lines of code.
- Works everywhere— Claude Desktop, Cursor, Windsurf, Copilot, and any MCP-compatible AI assistant

Prerequisite:Node.js20 or later. Verify withnode -v.

Add mcp-me to your AI assistant in one click — no path configuration needed (profile defaults to~/.mcp-me):

Claude Desktop:Download the latest.mcpbreleaseand double-click to install, or drag it into Claude Desktop → Settings → Extensions.

After installing, initialize your profile:

mcp-me init mcp-me generate --github your-username

This makes themcp-mecommand available everywhere on your system. No need to clone any repository — npm downloads the package for you.

mcp-me --help mcp-me init mcp-me generate --github your-username mcp-me serve

Alternative — run without installing(vianpx):

npxdownloads the package temporarily and runs it. Useful for trying mcp-me once, but slower on repeated use since it re-downloads each time.

Profile location:Commands default to~/.mcp-me. Override withMCP_ME_PROFILE_DIRor pass an explicit path:mcp-me serve ~/my-profile.

# 1. Initialize your profile (creates YAML templates + .mcp-me.yaml in ~/.mcp-me) mcp-me init # 2. Edit the config file — uncomment your sources code ~/.mcp-me/.mcp-me.yaml

generators: github: your-username devto: your-username bluesky: handle.bsky.social zodiac: aquarius plugins: github: enabled: true username: your-username

# 3. Generate! Reads sources from .mcp-me.yaml automatically mcp-me generate # 4. Start the MCP server mcp-me serve

CLI flags also work:mcp-me generate --github octocat --devto myuser

All commands work withnpx(zero install) or withmcp-medirectly if installed globally. Thegeneratecommand pulls your data from public APIs and auto-populates profile YAML files — no API keys needed for most sources.

~/.mcp-me/ → Default profile location .mcp-me.yaml → Configuration (generators + plugins) identity.yaml → Your data (name, bio, contact) skills.yaml → Your data (languages, tools) projects.yaml → Your data (portfolio) career.yaml → Your data (experience) interests.yaml → Your data (hobbies, topics) personality.yaml → Your data (traits, values) goals.yaml → Your data (short/long-term) faq.yaml → Your data (Q&A pairs)

Use the one-click install badgesabove. After installing, runmcp-me initto create your profile.

mcp-me ships as a full Open Pluginsplugin for Cursor. Install from cursor.directoryor clone the repo — the plugin auto-detects all components:

Validate the plugin structure:npm run validate:open-plugin

Add to~/.codeium/windsurf/mcp_config.json:

{ "mcpServers": { "me": { "command": "npx", "args": ["-y", "mcp-me", "serve"] } } }

Add to.cursor/mcp.jsonin your project root:

{ "mcpServers": { "me": { "command": "npx", "args": ["-y", "mcp-me", "serve"] } } }

Add to.vscode/mcp.jsonin your project root (or in your User Settings for global access):

{ "servers": { "me": { "command": "npx", "args": ["-y", "mcp-me", "serve"] } } }

Tip:To enable it globally (all workspaces), open VS Code Settings (Ctrl+Shift+P→ "Preferences: Open User Settings (JSON)") and add themcpkey there instead.

Option A — Desktop Extension (.mcpb, recommended):
- Downloadmcp-me.mcpbfromGitHub Releases
- Double-click the file, or drag it into Claude Desktop → Settings → Extensions
- Set your profile directory when prompted (default:~/.mcp-me)
- Runmcp-me initif you haven't created a profile yet

{ "mcpServers": { "me": { "command": "npx", "args": ["-y", "mcp-me", "serve"] } } }

AI agents read special Markdown files in your project to understand how they should behave. Pair them with mcp-me so thatevery AI session automatically consults your profile— no more repeating your stack, career, or preferences in every conversation.

# AGENTS.md — for Windsurf, Cline, Codex, etc. cp "$(npm root -g)/mcp-me/templates/AGENTS.md" ./AGENTS.md # GitHub Copilot mkdir -p .github cp "$(npm root -g)/mcp-me/templates/.github/copilot-instructions.md" .github/copilot-instructions.md

Both templates are included with mcp-me and tell the AI to callask_about_mewhenever context about you would improve the response.

See theAgent Instructions Guidefor examples, global setup, and tips on combining with project-specific rules.

Your profile is a collection of YAML files:

See Schema Referencefor full documentation.

Static profile data exposed as MCP resources:

- me://identity— Personal identity and contact
- me://career— Professional history
- me://skills— Skills and proficiencies
- me://interests— Hobbies and preferences
- me://personality— Personality traits and values
- me://goals— Personal and professional goals
- me://projects— Portfolio and projects
- me://faq— Frequently asked questions

- ask_about_me— Free-form question about the user
- search_profile— Keyword search across all profile data

- introduce_me— Generate a 2-paragraph introduction
- summarize_career— Summarize career trajectory
- technical_profile— Describe technical skills and stack
- collaboration_fit— Evaluate fit for a project

Generators run duringmcp-me generateto auto-populate your profile from public APIs or user-provided exports.No API keys neededfor most sources.

- Registered generators:329
- Generator source files:44 single-generator files + 15 batch files (src/generators/)

The table below is a curated list of commonly used generators. The complete source of truth issrc/generators/index.ts.

--blogger-backupimports written content from a Blogger XML export file on disk. It is designed for archived or multi-author blogs where you want to recover your posts even if the site is old, partially offline, or not easily queryable through a public API.

By default it imports all post entries from the file. If the backup contains multiple authors, append::author1,author2,...after the file path to keep only posts whose author name or email matches one of those values.

# Import all posts from a Blogger export mcp-me generate --blogger-backup ~/Downloads/blog-2026-03-24.xml # Import only posts written by specific authors/emails mcp-me generate --blogger-backup "~/Downloads/blog.xml::fernandopalad@gmail.com,fnpaladini@gmail.com,Fernando Paladini"

- Open Blogger and choose your blog.
- Go toSettings.
- InManage blog, clickBack up content.
- Download the XML file.
- Pass that file path to--blogger-backup.

Want to add a new data source? See the Generator Creation Guide.

Plugins run duringmcp-me serveand providereal-time datato AI assistants on every query.

plugins: github: enabled: true username: "your-username" spotify: enabled: true client_id_env: "SPOTIFY_CLIENT_ID" client_secret_env: "SPOTIFY_CLIENT_SECRET" refresh_token_env: "SPOTIFY_REFRESH_TOKEN"

Community plugins are installed from npm (mcp-me-plugin-*) and auto-discovered. See the Plugin Creation Guide.

# Auto-generate profile from multiple data sources mcp-me generate [--directory] --github <user> [--devto <user>] [--stackoverflow <id>] ... # Initialize with blank YAML templates (defaults to ~/.mcp-me) mcp-me init [directory] # Validate profile YAML files mcp-me validate [directory] # Start the MCP server (defaults to ~/.mcp-me) mcp-me serve [directory] # Scaffold a new generator or plugin (for contributors) mcp-me create generator <name> [--category <category>] mcp-me create plugin <name>

Profile location:Defaults to~/.mcp-me. Override withMCP_ME_PROFILE_DIRor pass an explicit[directory]argument.

# Clone the repo git clone https://github.com/paladini/mcp-me.git cd mcp-me # Install dependencies npm install # Run tests npm test # Build npm run build # Run in dev mode npm run dev

What is MCP (Model Context Protocol)?MCP is an open standard by Anthropic that connects AI assistants to external data sources. mcp-me uses MCP to let AI assistants read your personal profile data.

Do I need API keys?Most generators use public APIs with no auth needed. Some (Strava, Spotify) require tokens — see the.mcp-me.yamlcomments for details.

Can I use this with Claude Desktop / VS Code / Cursor / Windsurf?Yes! Any MCP-compatible AI assistant works. See theConfigure Your AI Assistantsection.

How do I make AI agents use my profile automatically?Drop anAGENTS.md(for Windsurf, Cline, Codex) or.github/copilot-instructions.md(for GitHub Copilot) into your project. Templates are included — see the Agent Instructions Guide.

How do I add a new data source?Runmcp-me create generator myserviceto scaffold a new generator, or see the Generator Creation Guide.

Is my data stored anywhere?No. All data stays local in your YAML files. The MCP server reads from disk — nothing is sent to any cloud.

How many generators are there?Currently 329 registered generators, implemented across 44 generator source files plus 15 batch files.

We welcome contributions! Whether it's a new plugin, a bug fix, or documentation improvements — see CONTRIBUTING.mdfor guidelines.

Maintainers: see Publishing Guidefor release and distribution instructions.

Provides AI assistants with advanced task management and memory capabilities using local JSON file storage.

Portable, cloud-hosted AI memory you own - structured memories, tasks, goals, and notes that work across Claude, ChatGPT, Gemini, and any MCP client.

Connect your Limitless Pendant data to Claude and other LLMs using the Limitless API.

Local-first cross-agent memory MCP. 6-layer structured brain (goal/context/emotion/impl/caveat/learning) with token-saving file diff cache (86% measured savings on re-reads)

A project management and session memory tool for AI agents to track projects, tasks, and context during chat sessions.

Give your AI the ability to remember key facts and everything you've ever discussed

Synchronizes memory templates across different Claude interfaces.

Centralized note store across AI clients: Claude, ChatGPT, Cursor, Codex, Windsurf. Save in one client, access in another instantly. Across devices — phone, desktop, everywhere. Cross-session context: 'catch me up' surfaces plans and findings from any prior session. AES-256-GCM encryption at rest, per-user key isolation. Soft delete with 30-day recovery window. Pin notes to exempt from cleanup and prioritize. Tag notes for categorization and filtering ('tag: auth'). Your mctx account is your identity — instant access from any AI tool.

An AI capability enhancement system providing professional roles, memory management, and knowledge systems for applications like Claude and Cursor.

AI conversation memory that works everywhere — save and recall across Claude, ChatGPT, Gemini, Cursor, and all MCP-compatible platforms. 11 tools including shared community memories.

mcp-me

About

Details

Jump to

Setup

About

Details

Jump to

Setup

More like this

Time

Context 7

1Panel

🔎 GPT Researcher

Serena

FastMCP v2 🚀