ssh-mcp
A centralized MCP gateway that gives AI agents controlled SSH
access over Streamable HTTP.

What problem does this solve?
Most MCP SSH servers run as local stdio processes โ one per
client, with no shared state, no centralized authorization, and
no audit trail. When multiple AI agents need SSH access, each
manages its own SSH keys and runs its own process. This creates:
- No centralized access control โ every client decides
what it can run
- No audit trail โ commands are invisible to the ops team
- SSH key sprawl โ keys scattered across every agent machine
- No rate limiting โ a runaway agent can overwhelm a target
ssh-mcp solves this by deploying a single HTTP gateway. All
clients connect to it; it connects to your SSH targets.
Authorization, rate limiting, connection pooling, and audit
logging happen in one place.
Quick Start
Using the pre-built image (recommended)
docker compose pull
docker compose up -d
The image is published at ghcr.io/gelse/ssh-mcp:latest.
The compose file maps host port 9080 to container port 8080.
Verify the server is running:
curl http://localhost:9080/health
Create a minimal config in config/ssh-mcp-config.json:
{
"version": 1,
"ssh_targets": {
"my-server": {
"host": "10.0.1.10",
"username": "deploy"
}
},
"allowed_commands": {
"default": [
{
"targets": ["*"],
"commands": ["hostname", "uptime", "free", "df"]
}
]
}
}
Generate an API key hash and add it to your config or
secrets.json (see Configuration).
Build locally instead
make build
docker compose up -d --build
Six MCP tools are available over Streamable HTTP:
| Tool | Description |
|---|
ssh_list_servers | List configured SSH targets |
ssh_list_allowed_commands | Show allowed commands for a target |
ssh_execute_command | Execute a command on a remote server |
ssh_check_connection | Test SSH connectivity to a target |
ssh_download_file | Download a file via SFTP |
ssh_upload_file | Upload a file via SFTP |
All tools follow the pattern ssh_<verb>_<noun>:
ssh_list_servers โ list resources
ssh_list_allowed_commands โ list permissions
ssh_execute_command โ perform an action
ssh_check_connection โ verify connectivity
ssh_download_file / ssh_upload_file โ file transfer
See examples/README.md for usage examples
including curl commands and Python client code.
What's configurable
ssh-mcp is configured via JSON files with hot-reload
(15 s poll, 2 s debounce). Key areas:
| Area | Details |
|---|
| SSH targets | Host, port, username, key, password |
| Command policies | Block patterns, per-key/network allowlists |
| Connection pool | Max connections, idle timeout, concurrency |
| Rate limiting | Per-IP sliding window (default 60 req/min) |
| Logging | JSONL with rotation, gzip, multiple targets |
| SFTP | Sandbox root, path length limits |
Full reference: docs/CONFIGURATION.md
| File | Purpose |
|---|
ssh-mcp-config.json | Main config |
config.schema.json | JSON Schema for validation |
secrets.json | Passwords and API key hashes |
MCP_SSH_* env vars | Overrides for any setting |
Why not just raw SSH / other MCP servers?
ssh-mcp adds a layered authorization chain (9 ordered layers)
between every client request and every SSH command. Per-API-key and
per-network rules let different agents get different permissions on
different servers โ without touching the underlying SSH accounts.
Additional protections:
- Circuit breakers isolate failing targets with exponential
backoff
- Rate limiting prevents runaway agents from overwhelming hosts
- Structured audit logs trace every command, client, IP, and
authorization decision
- Connection pooling reuses SSH sessions across requests
- Input sanitization and dangerous-pattern detection block
shell injection attempts
Architecture: ARCHITECTURE.md
Security model: docs/SECURITY.md
What it is NOT
- Not an interactive shell โ commands are executed
individually with structured output
- Not a file manager โ SFTP supports single-file download
and upload only (no directory listing or recursive transfer)
- Not a firewall / network ACL โ authorization is
command-level, not network-level
- Does not reduce SSH account privileges โ if a command is
allowed, the SSH user executes it with whatever privileges
that account has
Not yet / known gaps
Fixable with contribution:
- SFTP is single-file only โ no directory listing or recursive
transfer
- No TLS termination โ run Traefik or nginx in front
- No OAuth or mTLS app-layer authentication
- Rate limiter settings are not hot-reloadable (set at boot)
Architectural:
- Config API dashboard login sessions are in-memory only โ they
don't survive restarts and the API is single-instance (config
changes themselves persist to the config file normally)
- No tamper protection for audit logs
Observability
- Health:
GET /health โ returns {"status": "ok"}
- Metrics:
GET /metrics โ Prometheus exposition format
- Logging: Structured JSONL with request correlation
Full reference: docs/OBSERVABILITY.md
Config API & Dashboard
An optional web dashboard for managing configuration without
editing JSON files. Enable with CONFIG_API_ENABLED=true.
Full reference: docs/CONFIG-API.md
FAQ
Dashboard returns 401 over HTTP
The session cookie defaults to Secure (HTTPS only). For local
HTTP testing, set:
environment:
- CONFIG_API_SESSION_COOKIE_SECURE=false
Then restart the container.
How do MCP clients connect?
Connect to http://host:9080/mcp using the Streamable HTTP
transport. Pass your API key via X-API-Key or
Authorization: Bearer header.
How do I generate an API key hash?
docker compose exec mcp-ssh python -c \
"from lib.crypto import hash_api_key; print(hash_api_key('your-key'))"
Or use the hash utility in the Config API dashboard.
How does hot reload work?
The config file is polled every 15 seconds with a 2-second
debounce. Changes to targets, commands, and settings take effect
without restart. Rate limiter and log target settings require a
restart.
Why was my command denied?
Commands are evaluated through a 9-layer authorization chain.
The matched_via field in logs shows which layer denied.
See Security Model for the full chain.
How does rate limiting work?
Per-IP sliding window, default 60 requests per 60 seconds.
Exceeding the limit returns HTTP 503. Configure via
settings.rate_limit in the config file.
Where do logs go?
Logs are written to the /logs volume (mapped from ./logs).
The active log file is ssh-mcp.log in JSONL format with
optional gzip rotation.
Troubleshooting basics
curl http://localhost:9080/health
make config-test
docker compose logs mcp-ssh
Documentation
Development
make test
make integrationtest
See CONTRIBUTING.md for the full development
guide, coding conventions, and PR workflow.
Roadmap
No public roadmap. See
Not yet / known gaps for current
limitations and opportunities.
License
MIT