SSH Fleet MCP Server

io.github.inhuman/mcp-ssh-fleet

Repository Registry

What is the SSH Fleet MCP server?

Curated ssh_probe diagnostics and single-host ssh_exec over an allowlisted SSH fleet.

How to install SSH Fleet

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

SSH_FLEET_TRANSPORT
MCP transport. Must be 'stdio' for direct docker/stdio use.
SSH_FLEET_CMD_TIMEOUT_SECONDS
Per-host command timeout in seconds (1..600).
SSH_FLEET_OUTPUT_CAP_BYTES
Cap on output bytes per host section (>=256).
SSH_FLEET_PROBE_CONCURRENCY
Parallelism for ssh_probe.
SSH_FLEET_PROBE_MAX_HOSTS
Safety cap on the number of hosts in one probe.
SSH_FLEET_AUTH_TOKEN
secret
Optional X-MCP-AUTH bearer token (only used by the http/sse transports).

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-ssh-fleet": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/inhuman/mcp-ssh-fleet:0.1.5",
        "-v",
        "{inventory_path}:/etc/ssh-fleet/inventory.yaml:ro",
        "-v",
        "{key_path}:/etc/ssh-fleet/id_ed25519:ro"
      ],
      "env": {
        "SSH_FLEET_TRANSPORT": "<YOUR_SSH_FLEET_TRANSPORT>",
        "SSH_FLEET_CMD_TIMEOUT_SECONDS": "<YOUR_SSH_FLEET_CMD_TIMEOUT_SECONDS>",
        "SSH_FLEET_OUTPUT_CAP_BYTES": "<YOUR_SSH_FLEET_OUTPUT_CAP_BYTES>",
        "SSH_FLEET_PROBE_CONCURRENCY": "<YOUR_SSH_FLEET_PROBE_CONCURRENCY>",
        "SSH_FLEET_PROBE_MAX_HOSTS": "<YOUR_SSH_FLEET_PROBE_MAX_HOSTS>",
        "SSH_FLEET_AUTH_TOKEN": "<YOUR_SSH_FLEET_AUTH_TOKEN>"
      }
    }
  }
}

Related MCP servers

Exec Sandbox

Maintained

Single exec tool running caller Python in a network-isolated locked-down sandbox.

MIT

View repository →

Kubernetes Ephemeral Job

Maintained

Runs a command in a throwaway Kubernetes pod and returns exit code, output and artifacts.

MIT

View repository →

Inite Brain

Active

Open-source bitemporal memory layer for LLM agents with knowledge graphs and conflict resolution.

TypeScript

AGPL-3.0

View repository →

io.github.inity13/agentstack-mcp

Active

Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.

JavaScript

MIT

View repository →

io.github.inity13/decisionmatrix-mcp

Active

Deterministic multi-criteria decision analysis for AI agents — score, rank & explain options.

JavaScript

MIT

View repository →

io.github.inity13/precisioncalc-mcp

Active

High-precision finance & business calculations for AI agents — exact decimals, never floats.

Python

MIT

View repository →