hermes-fleet-mcp
Routes Docker operations (e.g., listing containers, viewing logs) across a fleet of Docker hosts via the Scotty API.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@hermes-fleet-mcplist all running containers on hostinger-01"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
hermes-fleet-mcp
MCP (Model Context Protocol) server that routes Docker operations across a fleet of Docker hosts via the Scotty API.
Overview
Provides two MCP tools:
fleet_route— Route a Docker operation through Scotty (Arcane MCP → target Docker host).fleet_hosts— List all known Docker hosts in the fleet.
Related MCP server: amp-mcp-server
Quick Start
Install
pip install hermes-fleet-mcpOr run from source:
pip install -e .Configure
Set environment variables (all optional):
Variable | Default | Description |
|
| Scotty API endpoint |
|
| JSON array of host identifiers |
Run
python -m hermes_fleet_mcpThe server communicates via stdio JSON-RPC.
Tool: fleet_route
Route a Docker operation through Scotty.
Parameters
Parameter | Required | Default | Description |
| Yes | — | The Docker operation to perform (e.g. "List all running containers", "Show container logs for nginx") |
| No |
| Target host identifier. Use |
| No |
| Optional context parameters (passed as additional context to Scotty) |
Examples
{
"tool": "fleet_route",
"arguments": {
"action": "List all running containers",
"host": "hostinger-01"
}
}{
"tool": "fleet_route",
"arguments": {
"action": "Show container logs for plex",
"host": "all"
}
}Tool: fleet_hosts
List all known hosts.
{
"tool": "fleet_hosts",
"arguments": {}
}Docker Deployment
docker build -t hermes-fleet-mcp .
docker run --rm -e SCOTTY_BASE_URL=http://scotty:8644/v1 hermes-fleet-mcpHermes Agent Registration
Add to ~/.hermes/profiles/<profile>/config.yaml:
mcp_servers:
fleet-mcp:
command: "python"
args: ["-m", "hermes_fleet_mcp"]
timeout: 120
connect_timeout: 15Architecture
MCP Client → hermes-fleet-mcp (stdio)
↓ POST /v1/chat/completions
Scotty (Hermes profile)
↓ Arcane MCP
Target Docker host(s)The server proxies Docker operation requests to Scotty's chat API. Scotty then routes through Arcane MCP to the appropriate Docker host(s). This means the server doesn't need direct Docker access — it delegates to the existing fleet management infrastructure.
Development
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"Run tests:
python3 tests/test_fleet_mcp.pyLicense
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MatsWeckhorst/hermes-fleet-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server