network_medic
Autonomous network monitoring and auto-remediation MCP server for Claude Desktop, enabling observation, planning, human-approved execution, verification, and session summarization.
README
network_medic
An autonomous network monitoring and auto-remediation MCP server for Claude Desktop.
Claude Desktop acts as the LLM brain — it observes the network state, decides the remediation plan, presents each action to the user for approval, executes, verifies, and summarises the session.
No separate Anthropic API key required.
Architecture
Observe → Plan (Claude Desktop) → Policy Validation → Human Approval → Execute → Verify → Log + Learn
MCP Tools
| Tool | Description |
|---|---|
observe_network |
Runs probes (connectivity, DNS, latency), returns state + diagnostic context |
execute_action |
Executes a single approved action |
verify_action |
Post-action probe diff — returns resolved / unchanged / degraded |
finalise_session |
Saves final state, returns session summary |
get_action_history |
View recent action log |
submit_feedback |
Rate the session outcome |
Project Structure
server/ MCP entry point + pipeline stage functions
modules/
monitor/ Observe — connectivity, DNS, latency probes
planner/ Context builder — prompt + memory injection
policy/ Safety — conflict checks, cooldowns, risk caps
remediate/ Execute — HIL gate, OS-specific commands
verifier/ Verify — post-action probe diff
rollback/ Recover — snapshot + revert
memory/ Persistent state — action log, state history, feedback
prompts/ LLM prompt templates
schemas/ JSON Schema contracts
utils/ Shared infrastructure
Setup
1. Clone the repo
git clone https://github.com/your-username/network_medic.git
cd network_medic
2. Create a virtual environment and install dependencies
python -m venv venv
# Windows
venv\Scripts\python.exe -m pip install -r requirements.txt
# Linux / macOS
source venv/bin/activate && pip install -r requirements.txt
3. Wire into Claude Desktop
Add to %APPDATA%\Claude\claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"network-medic": {
"command": "C:/path/to/network_medic/venv/Scripts/python.exe",
"args": ["C:/path/to/network_medic/server/mcp_server.py"],
"cwd": "C:/path/to/network_medic"
}
}
}
Replace C:/path/to/network_medic with your actual clone path.
Restart Claude Desktop after saving the config.
Local Debug Run
Runs the full pipeline in the terminal without Claude Desktop:
python main.py
Supported Platforms
- Windows
- Linux
- macOS
Requirements
- Python 3.13+
- Claude Desktop
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.