Atlas MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
π Atlas: Agentic MCP Workspace Assistant
Atlas is a professional-grade Model Context Protocol (MCP) ecosystem designed for workspace management and system orchestration. It features a reactive Gradio Dashboard and a high-performance MCP Server that bridges the gap between human users and AI agents.
π Key Features
π₯οΈ 1. Atlas Dashboard (app.py)
A modern, reactive multi-tab interface:
π€ Smart Assistant: Chat with an LLM that is directly connected to Atlas's local tools.
π Workspace Explorer: Live view of your project files with real-time status.
π System Monitor: Real-time gauges for CPU and Memory usage using
psutil.π Persistent Notes: A structured system to save and retrieve markdown notes.
ποΈ 2. Atlas MCP Server (atlas_server.py)
A comprehensive server that exposes your workspace to local agents (like Claude Desktop):
π οΈ Tools:
get_weather: Professional real-time weather integration.add_note/list_notes: File-system backed persistent storage.list_files/read_workspace_file: Secure-path-constrained file operations.
π Resources:
system://metrics: JSON-ready system stats.notes://{title}: Dynamic URI scheme for note retrieval.
Related MCP server: mon-serveur-mcp
ποΈ Architecture
graph TD
User[Human User] -->|Interacts| UI[Gradio Dashboard]
UI -->|Calls| Server[Atlas MCP Server]
Agent[Claude/GPT-4o] -->|Connects via stdio| Server
Server -->|Actions| Files[Local Filesystem]
Server -->|Monitoring| Sys[System Metrics]
Server -->|External| Weather[Open-Meteo API]π Getting Started
1. Prerequisites
Python 3.10+
Dependencies:
pip install mcp psutil gradio httpx
2. Run the Dashboard
python app.pyThis will launch a local server (usually at http://localhost:7860).
3. Connect as an MCP Server
To use these tools inside Claude Desktop, add this to your config:
{
"mcpServers": {
"atlas-assistant": {
"command": "python",
"args": ["/absolute/path/to/atlas_server.py"]
}
}
}ποΈ Project Structure
app.py: The reactive frontend.atlas_server.py: Core MCP logic & tools..notes/: Directory for persistent workspace data.simple_mcp/: Original fundamentals lab.
βοΈ License
MIT License. Created by good2idnan.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables file system operations, web scraping, and AI-powered search through MCP tools for use by LLM agents.1-
- FlicenseNot gradedqualityDmaintenanceExposes system tools (disk usage, file listing) and weather information via Open-Meteo to MCP-compatible LLMs.-
- AlicenseAqualityCmaintenanceEnables users to access local files, manage persistent notes via CRUD, fetch URLs, inspect system information, and analyze or transform text through MCP tools.11MIT
- AlicenseBqualityCmaintenanceEnables AI agents to run shell commands, execute Python code, read and write files, search text, and create or delete folders through MCP stdio tools.9MIT