ssh-mcp is an MCP server that enables AI assistants to securely execute commands and transfer files on remote servers via SSH. It integrates with your existing ~/.ssh/config for connection details.
list_servers: View all configured SSH servers, optionally filtered by group, showing names, groups, and descriptions.
list_groups: View all server groups with their descriptions and member counts.
execute: Run a shell command on a single SSH server with configurable timeout, working directory, and optional bypass of dangerous command detection.
execute_on_group: Run a shell command in parallel across all servers in a group, with fail-fast mode and per-server timeouts.
upload_file: Upload a local file to a remote server via SFTP, with path validation to prevent sensitive file access.
download_file: Download a file from a remote server to a local destination via SFTP, with path validation on both ends.
Security & deployment features include dangerous command detection, automatic credential redaction in logs, connection pooling, host key verification, JSON audit logging, and flexible deployment via stdio or HTTP transport (suitable for Docker/network environments).
Supported as a TLS-terminating reverse proxy option for securing HTTP transport deployments in production environments.
Supports Datadog log integration through JSON log format output, allowing structured logging events to be consumed by Datadog's log aggregation platform.
Provides Docker container deployment options with prebuilt images, volume mounting for SSH configuration, and containerized execution environments.
Hosts the project repository and publishes Docker images to GitHub Container Registry for containerized deployments.
Mentioned as a use case for traffic patterns that influenced HTTP keepalive timeout configuration optimizations.
Supported as a TLS-terminating reverse proxy option for securing HTTP transport deployments in production environments.
Built with Python 3.11+ and provides pip installation options, though this is primarily an implementation detail rather than a target service.
Supports Splunk log integration through JSON log format output, allowing structured logging events to be consumed by Splunk's log aggregation platform.
Uses TOML format for server configuration files, defining server groups, descriptions, and organizational structure for SSH infrastructure.
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., "@ssh-mcp check the disk usage on all servers in the production group"
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.
SSH MCP server that lets AI assistants execute commands on remote servers.
ssh-mcp is a Model Context Protocol server that gives AI assistants like Claude direct access to your SSH infrastructure. Once configured, Claude can run commands, transfer files, and query server groups across your fleet without leaving the conversation.
Connection details are read from your existing ~/.ssh/config. No credentials are stored in the MCP configuration.
Related MCP server: ssh-mcp-server
Run shell commands on individual servers or across entire groups in parallel
SFTP file upload and download over the existing SSH session
Connection pooling — reuses SSH connections across tool calls
Dangerous command detection — warns before executing destructive operations
Server groups for organizing hosts (production, staging, per-service)
SSH config integration — reads host, port, user, and identity from ~/.ssh/config
Custom config path via SSH_MCP_CONFIG environment variable
dry_run previews — see which server, command, working directory and timeout would be used, without connecting
SFTP local-path confinement — every local path stays inside a configured transfer_root
stdio or streamable-HTTP transport, with bearer-token auth for network deployments
Built-in ssh-mcp healthcheck subcommand for Docker's HEALTHCHECK
Optional OpenTelemetry tracing via the otel extra
# Run directly with uvx (no install required)
uvx blc-ssh-mcp
# Or install with pip
pip install blc-ssh-mcpRequires Python 3.11+. Install uv to use uvx.
The PyPI package is
blc-ssh-mcp, notssh-mcp. The namessh-mcpon PyPI belongs to an unrelated project by a different author. Installing it will not give you this server. Releases before 0.6.1 documented the wrong name — if you followed those instructions, uninstallssh-mcpand installblc-ssh-mcp.
A prebuilt image is published to GitHub Container Registry:
docker pull ghcr.io/blackaxgit/ssh-mcp:latestOr run with Docker Compose:
services:
ssh-mcp:
image: ghcr.io/blackaxgit/ssh-mcp:latest
stdin_open: true
restart: unless-stopped
environment:
SSH_MCP_CONFIG: /config/servers.toml
volumes:
- ./servers.toml:/config/servers.toml:ro
- ~/.ssh:/home/sshmcp/.ssh:roThe image uses a non-root sshmcp user (uid 1000). Mount your SSH keys and config file read-only. compose.yaml in the repo carries a fuller example — it builds from the local Dockerfile rather than pulling the published image, and includes the HTTP-transport service, ulimits and healthcheck guidance omitted above.
mkdir -p ~/.config/ssh-mcp
cp config/servers.example.toml ~/.config/ssh-mcp/servers.tomlEdit ~/.config/ssh-mcp/servers.toml and add your servers. Server names must match Host entries in ~/.ssh/config.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your platform:
{
"mcpServers": {
"ssh-mcp": {
"command": "uvx",
"args": ["blc-ssh-mcp"]
}
}
}To use a non-default config path, pass the environment variable:
{
"mcpServers": {
"ssh-mcp": {
"command": "uvx",
"args": ["blc-ssh-mcp"],
"env": {
"SSH_MCP_CONFIG": "/path/to/servers.toml"
}
}
}
}Restart Claude Desktop after editing the config.
If you use Claude Code instead of Claude Desktop, you can set everything up from the terminal:
# 1. Add the MCP server
claude mcp add ssh-mcp -- uvx blc-ssh-mcp
# 2. Create the config directory and copy the example
mkdir -p ~/.config/ssh-mcp
curl -sL https://raw.githubusercontent.com/blackaxgit/ssh-mcp/main/config/servers.example.toml \
> ~/.config/ssh-mcp/servers.toml
# 3. Edit with your servers (server names must match ~/.ssh/config Host entries)
${EDITOR:-nano} ~/.config/ssh-mcp/servers.toml
# 4. Restrict permissions
chmod 600 ~/.config/ssh-mcp/servers.tomlTo use a custom config path:
claude mcp add ssh-mcp -e SSH_MCP_CONFIG=/path/to/servers.toml -- uvx blc-ssh-mcpVariable | Default | Purpose |
| — | Absolute path to a TOML config file. Overrides the default search path. |
|
| Log output format. Set to |
|
| MCP transport. |
|
| Bind address for HTTP transport. Binding to any non-localhost value (e.g. |
|
| TCP port for HTTP transport. |
| — | Shared bearer secret. When set, every request must carry |
| — | Path to a file containing the bearer token (alternative to |
|
| Authentication mode. |
| — | Magic-string escape hatch. Must equal literal |
|
| uvicorn |
|
| uvicorn |
|
| uvicorn |
|
| Set to |
| — | Comma-separated extra Host-header values the SDK's DNS-rebinding protection should permit (e.g. |
|
| Directory SFTP transfers are confined to. Takes precedence over |
|
| Honoured when searching for |
|
| Base directory for the default transfer root. |
|
| For local development / CI only. Set to |
fd exhaustion mitigation: the Docker base image inherits a 1024 fd limit by default. Under sustained burst traffic that can run out quickly. Raise it in your compose file:
ssh-mcp:
# ...
ulimits:
nofile:
soft: 65536
hard: 65536Pair that with the SSH_MCP_HTTP_KEEPALIVE_TIMEOUT / SSH_MCP_HTTP_LIMIT_CONCURRENCY knobs above for a full fix.
ssh-mcp exposes the MCP streamable HTTP transport as an alternative to stdio. This lets MCP-aware clients connect over the network instead of launching a subprocess, which is useful for containerized deployments, shared-team servers, or anything that needs to survive a client restart.
WARNING: ssh-mcp serves plain HTTP, not HTTPS. The bearer token is transmitted in cleartext on every request. Deploying on a public IP without a TLS-terminating reverse proxy (Caddy, nginx, Traefik) exposes the token to any network observer — equivalent to publishing a root shell. Always terminate TLS before ssh-mcp reaches the network.
Security first. ssh-mcp runs shell commands on remote servers. Exposing the HTTP endpoint without authentication is equivalent to exposing a root shell. The startup code enforces this:
Binding to 127.0.0.1 / localhost / ::1 without a token is allowed — this matches the single-user workstation model.
Binding to ANY other address without SSH_MCP_HTTP_TOKEN raises RuntimeError at startup and the process exits.
The MCP SDK's DNS-rebinding protection is enabled by default. Remote clients connecting via a hostname must have it listed in SSH_MCP_HTTP_ALLOWED_HOSTS.
Bearer-token comparison uses hmac.compare_digest to prevent timing attacks.
Local loopback (no auth needed):
SSH_MCP_TRANSPORT=http ssh-mcp
# → listening on http://127.0.0.1:8000/mcpContainer deployment with bearer auth:
TOKEN=$(openssl rand -hex 32)
docker run -d \
-p 8000:8000 \
-e SSH_MCP_TRANSPORT=http \
-e SSH_MCP_HTTP_HOST=0.0.0.0 \
-e SSH_MCP_HTTP_TOKEN="$TOKEN" \
-e SSH_MCP_HTTP_STATELESS=true \
-e SSH_MCP_HTTP_ALLOWED_HOSTS='ssh-mcp.internal:*' \
-v ~/.ssh:/home/sshmcp/.ssh:ro \
-v ./servers.toml:/config/servers.toml:ro \
-e SSH_MCP_CONFIG=/config/servers.toml \
ghcr.io/blackaxgit/ssh-mcp:latestClients connect with:
Authorization: Bearer <TOKEN>
Host: ssh-mcp.internalFor stateful sessions (default), FastMCP maintains per-client context across requests. For stateless deployments behind a load balancer, set SSH_MCP_HTTP_STATELESS=true — each request is handled independently with no server-side session.
The Docker image includes a built-in ssh-mcp healthcheck CLI subcommand that
Docker's HEALTHCHECK directive invokes automatically. No inline Python, no
curl, no manual compose surgery required. The subcommand:
Auto-detects the transport via SSH_MCP_TRANSPORT:
stdio mode: verifies the package imports and servers.toml parses
http mode: sends a real MCP initialize JSON-RPC POST and checks for any non-5xx response
Reads the same auth env vars as the server (SSH_MCP_HTTP_TOKEN, SSH_MCP_HTTP_TOKEN_FILE, SSH_MCP_HTTP_AUTH) — never logs the token
Exits 0 if healthy, 1 otherwise
Uses Python stdlib only (no curl/wget dependency)
Applies a 3-second timeout to the HTTP probe. The stdio probe has no timeout of its own and relies on Docker's --timeout=5s (importing the server costs ~0.3s)
Run manually for debugging:
docker exec ssh-mcp ssh-mcp healthcheck && echo "healthy"Check current status:
docker inspect ssh-mcp --format '{{.State.Health.Status}}'To override the baked-in settings in your compose file:
healthcheck:
test: ["CMD", "ssh-mcp", "healthcheck"]
interval: 15s
timeout: 5s
retries: 3
start_period: 10sTracing is optional and off unless opentelemetry-api is importable:
uv pip install 'ssh-mcp[otel]'The extra installs the API layer only — the SDK and exporter are yours to choose, so ssh-mcp stays lightweight for anyone who does not trace. Install and configure opentelemetry-sdk plus an exporter (OTLP, Jaeger, Tempo) yourself; without an SDK the API is a no-op and nothing is emitted.
Spans produced:
mcp.tool.<name> — one per MCP tool call, tagged mcp.tool.name. Exceptions are recorded with StatusCode.ERROR.
ssh.execute, ssh.upload, ssh.download — the SSH/SFTP operation inside the tool call.
Span attributes go through the same credential redaction as the audit log (see Security).
If your reverse proxy (Caddy, nginx, Traefik, Envoy, Cloudflare Access, etc.) already authenticates requests before they reach ssh-mcp, you can disable the built-in bearer middleware with SSH_MCP_HTTP_AUTH=none. This mode is deliberately hard to enable on a public bind — you must also set a verbose acknowledgement env var:
docker run -d \
--network internal \
-e SSH_MCP_TRANSPORT=http \
-e SSH_MCP_HTTP_HOST=0.0.0.0 \
-e SSH_MCP_HTTP_AUTH=none \
-e SSH_MCP_HTTP_NETWORK_NO_AUTH=I_ACCEPT_RCE_RISK \
-e SSH_MCP_HTTP_ALLOWED_HOSTS='ssh-mcp.internal:*' \
-v ~/.ssh:/home/sshmcp/.ssh:ro \
-v ./servers.toml:/config/servers.toml:ro \
-e SSH_MCP_CONFIG=/config/servers.toml \
ghcr.io/blackaxgit/ssh-mcp:latestWARNING: SSH_MCP_HTTP_AUTH=none + SSH_MCP_HTTP_NETWORK_NO_AUTH=I_ACCEPT_RCE_RISK is a remote code execution surface. The magic-string acknowledgement exists so operators physically type the words "I ACCEPT RCE RISK" before opting in. Every tool call reaches a shell on every managed SSH server. Use this only when:
ssh-mcp is on a private Docker network not reachable from the host's public interface, AND
The reverse proxy fronting it enforces authentication (basic auth, OAuth, mTLS, Cloudflare Access, etc.), AND
You have audit logging on the proxy that's immutable to the ssh-mcp process.
For localhost binds without auth, no acknowledgement is needed — that matches the historical stdio deployment model.
Checked in order:
$SSH_MCP_CONFIG environment variable
$XDG_CONFIG_HOME/ssh-mcp/servers.toml, falling back to ~/.config/ssh-mcp/servers.toml (default)
config/servers.toml relative to the package (development only)
Example servers.toml:
[settings]
ssh_config_path = "~/.ssh/config"
command_timeout = 30 # SSH *connect* timeout in seconds, range 1..3600
max_output_bytes = 51200 # truncate captured output at this many bytes, per stream
max_command_bytes = 65536 # reject longer command strings at the tool boundary (1024..1048576)
connection_idle_timeout = 300 # seconds; eviction scan runs every 60s
known_hosts = true # false removes MITM protection
max_parallel_hosts = 10 # process-wide concurrency cap for group execution (1..100)
[groups]
production = { description = "Production servers" }
staging = { description = "Staging servers" }
[servers.web-prod-01]
description = "Production web server"
groups = ["production"]
[servers.web-staging-01]
description = "Staging web server"
groups = ["staging"]
jump_host = "bastion"
[servers.db-prod-01]
description = "Production database"
groups = ["production"]
user = "dbadmin"Note two things about the timeouts, because the names invite confusion:
command_timeout is the SSH connection-establishment timeout, not the command execution timeout.
Per-command timeout comes from the timeout argument of execute / execute_on_group (default 30) — unless the server block sets timeout = N, which wins over the caller's argument.
max_parallel_hosts bounds the whole process, not a single call: the semaphore is built once at startup, so concurrent execute_on_group calls share the same budget rather than each getting their own.
Per-server overrides (hostname, port, user, identity_file, jump_host, default_dir, timeout) take precedence over ~/.ssh/config. See config/servers.example.toml for the annotated reference.
Restrict config file permissions to your user:
chmod 600 ~/.config/ssh-mcp/servers.tomlTool | Description |
| List configured servers; optionally filter by group |
| List server groups with member counts |
| Run a shell command on a single server (supports |
| Run a command on all servers in a group (parallel; supports |
| Upload a file to a server via SFTP. Local path is relative to |
| Download a file from a server via SFTP. Local path is relative to |
dry_run=true on either execute tool returns a [DRY RUN] preview of the server, command, working directory, timeout and force flag without opening a connection. Dangerous-command detection still runs, so a rejection can be previewed; if force=true would bypass a match, the preview carries an explicit ⚠️ DANGEROUS banner.
Command strings longer than max_command_bytes (default 65536 encoded UTF-8 bytes) are rejected at the tool boundary, before redaction or dangerous-command matching runs. Single SFTP transfers are capped at 100 MiB: an oversized upload is refused outright, an oversized download only logs a warning (the bytes are already on disk). Use rsync or scp for anything larger.
Dangerous command blocking. ssh-mcp rejects commands that match known destructive patterns unless the tool caller passes force=true:
Recursive deletes of /, ~, $HOME, $USER — combined (rm -rf /) and split (rm -r -f /, rm --recursive --force /) flag forms, in any flag order
find / -delete, find / -exec rm
Block-device wipes: shred /dev/*, wipefs /dev/*, blkdiscard /dev/*, sgdisk -Z /dev/*
Partition-table destruction: parted /dev/… mklabel, fdisk /dev/sd*
mkfs, dd if=… and the reordered dd of=… if=… form
Redirects into a block device or auth database: > /dev/sd*, > /dev/nvme*, > /dev/hd*, > /etc/{passwd,shadow,gshadow,sudoers}
chmod 777 / — flag before or after the mode (chmod -R 777 /, chmod 777 -R /)
Fork bombs (spaced and adjacent variants)
Payload-execution wrappers: base64 -d | bash|sh|zsh|python|perl|ruby, eval "…", python|python3|perl|ruby -c, bash -c
Note the last bullet — it catches ordinary commands too.
bash -c '…',python3 -c '…'andeval …are blocked by default even when entirely benign. Wrap them differently (a script file, a heredoc) or passforce=truefor an audited call.
ASCII control characters (null bytes, newlines, \x01..\x1f, \x7f) are normalized to spaces before matching, so rm\x00-rf / is caught just like rm -rf /. The regex is fuzz-tested with Hypothesis on every CI run.
This is a TRIPWIRE, not a security boundary. The regex catches obvious accidents and shortcut destructive commands. It does NOT defend against a motivated attacker:
The base64/
eval/-cwrappers above are matched literally; any rewrite the regex does not spell out (a different decoder, a temp file,sh <<'EOF') gets throughShell hex escapes (
$'\x72\x6d -rf /') are interpreted AFTER regex matchingUnicode homoglyphs (Cyrillic
р, Greekρ) do not match LatinrIndirection via
$(...)and`...`can hide intent — those are not matched at allIf you need real isolation for untrusted tool callers, sandbox at a lower layer: run ssh-mcp inside a container with a restricted SSH config, use
ForceCommandon the managed servers, or auditforce=falseusage via the structured logs. The dangerous-command filter exists to stop LLM accidents and typos, not adversaries.
The bypass is not recorded in the audit log. Audit records carry server, command, exit_code and duration_ms only; force is emitted solely as an OpenTelemetry span attribute (ssh.force), and therefore only when the optional otel extra is installed and an exporter is configured. A block is logged as a warning on the operational logger, not the audit logger. If you need a paper trail for bypasses, export traces or withhold force=true at the MCP client. Do not grant force=true to untrusted MCP clients.
Credential redaction in logs. ssh-mcp automatically redacts known credential patterns (MySQL -p<pass>, --password=, PGPASSWORD=, Authorization: Bearer, URL basic-auth user:pass@host, plus any env var ending in _PASSWORD, _SECRET, _TOKEN, _KEY, _CREDENTIAL, _PWD) from audit logs and OTel span attributes before they reach stderr or trace backends. The asyncssh internal channel logger is suppressed to WARNING level so it never emits the raw command.
Known limitation: command OUTPUT is NOT redacted. If you run
cat /etc/mysql/my.cnf,env | grep PASSWORD, orkubectl get secret X -o yaml, the stdout/stderr returned to the MCP client will contain plaintext secrets. The redaction pipeline only filters the COMMAND string (what you asked to run), not the OUTPUT (what it printed). Avoid running commands that print secrets via ssh-mcp — pass credentials through env vars, Docker/K8s secrets, or dedicated config files instead.
Local path confinement (new in 0.6.0; versions ≤ 0.5.6 are affected by the flaw it fixes — see CHANGELOG.md). SFTP upload_file and download_file no longer accept arbitrary absolute local paths. Every local path is relative to a configured transfer root and is resolved one component at a time beneath it, refusing a symbolic link at any component:
[settings]
transfer_root = "~/.local/share/ssh-mcp/transfers" # default; honours $XDG_DATA_HOMEOverride with the SSH_MCP_TRANSFER_ROOT environment variable. The directory is created 0700 on demand, must be owned by the user running ssh-mcp, and must not itself be a symlink — ssh-mcp refuses to start a transfer otherwise.
Consequences, all deliberate:
Absolute local paths and .. are rejected. Sub-directories are allowed, but they must already exist.
Downloads do not overwrite. An existing destination fails rather than being silently replaced. A failed transfer removes its own partial file.
Remote non-regular files (symlinks, devices, FIFOs) are refused on a best-effort basis. SFTP protocol v3 offers no atomic no-follow open, so a remote server that swaps the file between the check and the open can still win that race; the local destination stays confined regardless.
Remote paths keep the existing sensitive-path denylist — a tripwire, not a boundary, matched as a substring after normalizing // and ./ away, case-insensitively. It covers /etc/{shadow,gshadow,passwd,sudoers} and /etc/ssh/ssh_host_*; .ssh/{authorized_keys,id_rsa,id_ed25519,id_ecdsa,id_dsa,identity,config,known_hosts}; .aws/{credentials,config}, .azure/accesstokens.json, .config/gcloud/{credentials,access_tokens}.db; .kube/config, /etc/kubernetes/{admin,kubelet}.conf, /var/lib/kubelet/pki/; .netrc, .pgpass, .git-credentials, .docker/config.json; /proc/{self,<pid>}/{environ,mem,cmdline,maps,stack,status}, /proc/{kcore,kallsyms}; the MySQL / PostgreSQL / MongoDB data directories under /var/lib/; and the Windows SAM / SECURITY hives plus \users\administrator\.ssh\. Public keys are **not** exempt — the old *.pub carve-out was a string check on a caller-supplied name and was removed.
Prior versions validated the caller's path string against a denylist and then handed that string to asyncssh, which resolved it independently — so anything not enumerated was writable. Confinement replaces enumeration: ssh-mcp opens the local file itself and never lets a caller-supplied path reach the SFTP library.
Migrating from ≤ 0.5.x: replace absolute local paths with names relative to transfer_root, or set transfer_root to the directory you were already using. There is no flag to restore the old behaviour.
Host key verification is on by default (known_hosts = true). Disabling StrictHostKeyChecking in ~/.ssh/config weakens MITM protection and should be avoided in production.
Audit logging. Every tool call is logged to stderr with server, command, exit_code, duration_ms, and (for SFTP) byte counts. SFTP operations emit three-stage events: sftp.upload.start → sftp.upload.complete (or sftp.upload.failed), each tagged with a stable connection_id so a single transfer is grep-correlatable.
For production log aggregation, set SSH_MCP_LOG_FORMAT=json to emit single-line JSON events:
{"event": "sftp.upload.complete bytes=4096 duration_ms=183", "level": "info", "timestamp": "2026-04-08T16:00:11.761575Z", "server": "web-prod-01", "operation": "upload", "local_path": "releases/app.tar.gz", "remote_path": "/var/www/release.tar.gz", "connection_id": "web-prod-01-4242-a3f1c9d2"}When running in Docker, capture stderr with docker logs for the audit trail.
For vulnerability reports, see SECURITY.md. Do not open public GitHub issues for security concerns.
git clone https://github.com/blackaxgit/ssh-mcp.git
cd ssh-mcp
uv sync --locked --extra dev
uv run pytest
uv run ruff check src/ tests/See CONTRIBUTING.md for guidelines on making changes and submitting pull requests.
See CHANGELOG.md.
Mozilla Public License 2.0. See LICENSE.
Download a file from a remote server via SFTP.
Args: server: Server name (e.g. 'pro-dicentra'). remote_path: Absolute path to remote file. local_path: Absolute local destination path.
Returns: Confirmation message with file size.
| Name | Required | Description | Default |
|---|---|---|---|
| server | Yes | ||
| local_path | Yes | ||
| remote_path | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the SFTP protocol and describes the return value, but doesn't cover important behavioral aspects like error conditions, timeout behavior, authentication requirements, file size limitations, or whether the operation is idempotent. The description provides basic operational context but lacks comprehensive behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (purpose, Args, Returns) and uses minimal sentences. Each sentence earns its place by providing essential information. The formatting is efficient, though the 'Args:' and 'Returns:' labels could be slightly more concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema (which handles return value documentation), no annotations, and 3 parameters with good description coverage, the description is reasonably complete. It covers the core operation, all parameters, and return format. The main gap is lack of behavioral context like error handling and authentication requirements, but the presence of output schema reduces the completeness burden.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description compensates by clearly explaining all three parameters with examples and context. The Args section provides meaningful semantics: 'server' is explained with an example format, 'remote_path' specifies it must be absolute, and 'local_path' clarifies it's the destination. This adds substantial value beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Download a file') and resource ('from a remote server via SFTP'), distinguishing it from sibling tools like upload_file. It provides a complete verb+resource+protocol combination that leaves no ambiguity about what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like upload_file or other sibling tools. It mentions SFTP protocol but doesn't specify prerequisites, authentication requirements, or when this tool is appropriate versus other file transfer methods. No exclusions or alternative scenarios are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a shell command on a single SSH server.
Args:
server: Server name (e.g. 'web-prod-01'). Must match a configured server.
Use list_servers to see available servers.
command: Shell command to execute on the remote server (exactly as it
would be typed at a bash prompt).
timeout: Command timeout in seconds. Default 30. Range 1–3600.
working_dir: Absolute remote directory to cd into before running the
command. Uses the server's default_dir from servers.toml
if omitted, or the SSH login directory if neither is set.
force: If True, bypass the dangerous-command detection regex. Use only
for audited bulk operations — the block list catches rm -rf /,
mkfs, dd-to-disk, chmod 777 /, and fork bombs. Default False.
dry_run: If True, do NOT connect or execute. Return a preview describing
what would run (server, command, working_dir, timeout, force).
Dangerous-command detection still runs so rejection can be
previewed. Useful for LLM plans that want to validate intent
before committing. Default False.
Returns:
Formatted command execution result with stdout, stderr, and exit code.
Long output is truncated at max_output_bytes (default 50 KiB).
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | ||
| server | Yes | ||
| command | Yes | ||
| dry_run | No | ||
| timeout | No | ||
| working_dir | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully covers behavioral traits: dangerous-command detection (with force bypass), timeout range (1–3600 seconds), output truncation at max_output_bytes, working_dir fallback logic, and dry_run behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with an Args section and Returns, and every sentence adds value. It is somewhat lengthy but justified by the number of parameters and behaviors; minor trimming could improve conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 6 parameters, no annotations, and presence of output schema (mentioned in Returns), the description thoroughly covers all aspects: parameter details, defaults, edge cases, behavior, and return format. It leaves no critical gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, but the description adds detailed semantics for all 6 parameters: server format and validation, command as bash, timeout units and range, working_dir fallback, force bypass details, and dry_run preview purpose. It also explains return value formatting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Execute a shell command on a single SSH server.' It uses a specific verb ('execute') and resource ('shell command on a single SSH server'), and distinguishes from sibling tools like 'execute_on_group' which targets groups, and file operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says 'on a single SSH server' and references 'list_servers' to see available servers, implying when to use this tool. It also notes 'dry_run' for validating intent before committing, and by context, alternatives like 'execute_on_group' exist for group execution.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a shell command on all servers in a group in parallel.
Concurrency is capped by the max_parallel_hosts setting (default 10;
configure in [settings] of servers.toml, range 1–100).
Args:
group: Group name (e.g. 'production', 'web'). Use list_groups to see
available groups.
command: Shell command to execute on every server in the group.
timeout: Per-server command timeout in seconds. Default 30.
Each server has its own timer; slow servers do NOT extend the
per-server limit for others.
working_dir: Absolute remote directory to cd into on each server.
Uses each server's default_dir if omitted.
fail_fast: If True, cancel remaining tasks as soon as any server
returns a non-zero exit code or errors. Default False —
run all servers to completion and report each result.
force: If True, bypass the dangerous-command detection regex. Use only
for audited bulk operations. Default False.
dry_run: If True, do NOT connect or execute anywhere. Return a
per-server preview describing what would run. Dangerous-
command detection still applies. Useful for previewing
fleet-wide rollouts before committing. Default False.
Returns: Formatted summary showing per-server results, success/failure counts, and aggregate exit status.
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | ||
| group | Yes | ||
| command | Yes | ||
| dry_run | No | ||
| timeout | No | ||
| fail_fast | No | ||
| working_dir | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: concurrency via max_parallel_hosts, per-server timeout behavior, fail_fast cancelation, force bypass of dangerous-command detection, dry_run preview, and return format. No contradiction with any missing annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear opening sentence, numbered args, and a return summary. It is slightly verbose in places (e.g., 'Each server has its own timer' could be shorter), but every sentence adds value. Overall, it's efficient and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, parallel execution, multiple flags), the description covers all necessary aspects: concurrency settings, per-server timeout, failure modes, dangerous-command detection, dry-run preview, and return format. The presence of an output schema reduces the need for detailed return description, and the provided summary is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must explain all parameters. It does so comprehensively: group (with reference to list_groups), command, timeout (with range and per-server independence), working_dir (with fallback to default_dir), fail_fast (with default behavior), force (with caution), and dry_run (with behavior description). Each adds meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the purpose: 'Execute a shell command on all servers in a group in parallel.' The verb 'Execute' and resource 'shell command on all servers' are specific. It distinguishes from siblings like 'execute' (likely single server) and 'list_groups' (discovery).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (executing on a group) and references 'list_groups' for discovering groups. It lacks an explicit statement of when not to use it (e.g., for single server operations), but the sibling context implies that 'execute' would be appropriate then.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all server groups with descriptions and member counts.
Returns: Formatted table of groups with name, description, and server count.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the return format ('Formatted table') and what columns to expect, which is helpful. However, it doesn't mention important behavioral aspects like whether this requires authentication, has rate limits, returns all groups at once or uses pagination, or if there are any access restrictions. The description adds some value but leaves significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately concise with two clear sentences. The first sentence states the core functionality, and the second describes the return format. There's no wasted text, though the structure could be slightly improved by combining the two sentences more fluidly or adding a brief introductory phrase.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has zero parameters, 100% schema coverage, and an output schema exists, the description is reasonably complete for a simple read operation. However, with no annotations and a read operation that likely has behavioral considerations (authentication, data scope, etc.), the description should ideally mention at least basic context about access or limitations. The output schema will handle return structure details, but behavioral transparency remains a gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters (schema coverage 100%), so the description doesn't need to explain parameters. The baseline for zero parameters is 4, as there's no parameter documentation burden. The description appropriately focuses on what the tool does rather than parameter details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('List') and resource ('server groups'), including what information is returned (descriptions and member counts). It distinguishes from sibling 'list_servers' by focusing on groups rather than individual servers. However, it doesn't explicitly differentiate from other potential group-related operations that might exist in the future.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. While it implicitly suggests this is for viewing group information rather than executing operations (like 'execute_on_group'), there are no explicit when/when-not instructions or references to sibling tools. The agent must infer usage context from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all configured SSH servers with their groups and descriptions.
Args: group: Optional group name to filter by. Shows all servers if omitted. Use list_groups to see available group names.
Returns: Formatted table of servers with name, groups, and description.
| Name | Required | Description | Default |
|---|---|---|---|
| group | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool returns a 'formatted table' which adds useful context about output format, but doesn't mention potential limitations like pagination, rate limits, or authentication requirements for accessing server configurations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly structured and concise: a clear purpose statement followed by well-organized Args and Returns sections. Every sentence earns its place by providing essential information without redundancy, and the information is front-loaded appropriately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (1 parameter, read-only operation), the description is quite complete. It explains purpose, parameter usage, and output format. With an output schema present, it doesn't need to detail return values further. The only minor gap is lack of explicit mention that this is a read-only operation, though that's implied by 'List'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate fully. It does this excellently by explaining the single parameter's purpose ('Optional group name to filter by'), behavior ('Shows all servers if omitted'), and relationship to other tools ('Use list_groups to see available group names'), adding substantial meaning beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('List all configured SSH servers') and resources ('SSH servers'), and distinguishes it from siblings by mentioning 'groups and descriptions' which aren't covered by other tools like execute or download_file.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool vs alternatives: it mentions using 'list_groups to see available group names' for filtering, and specifies that the group parameter is optional for showing all servers, giving clear context for usage decisions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Upload a file to a remote server via SFTP.
Args: server: Server name (e.g. 'pro-dicentra'). local_path: Absolute path to local file. remote_path: Absolute destination path on remote server.
Returns: Confirmation message with file size.
| Name | Required | Description | Default |
|---|---|---|---|
| server | Yes | ||
| local_path | Yes | ||
| remote_path | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions SFTP (implying secure transfer) and the return format, but doesn't cover critical behavioral aspects like authentication requirements, error handling, file size limits, overwrite behavior, or network timeouts. For a mutation tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections (purpose, args, returns) and uses minimal sentences that each serve a purpose. The first sentence states the core function, followed by organized parameter explanations and return information. It could be slightly more concise by integrating the parameter explanations more fluidly, but overall it's efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a mutation tool with 3 parameters, no annotations, and an output schema (which handles return values), the description covers the basic purpose and parameters adequately. However, it lacks important contextual details like authentication requirements, error conditions, or performance characteristics that would be helpful for safe and effective use. The presence of an output schema reduces the need to explain returns, but other gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description fully compensates by explaining all three parameters with clear examples and context. It specifies 'server' as a server name with an example, 'local_path' as an absolute path to the source file, and 'remote_path' as an absolute destination path. This adds substantial meaning beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Upload a file') and resource ('to a remote server via SFTP'), distinguishing it from sibling tools like download_file (which performs the inverse operation) and execute/execute_on_group (which run commands rather than transfer files). The verb+resource combination is precise and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context through the mention of SFTP and parameter explanations, but doesn't explicitly state when to use this tool versus alternatives like download_file or when not to use it (e.g., for local file operations). It provides basic guidance through parameter descriptions but lacks explicit comparative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.1execute1 field changedInput schema / properties / dry_runAdded value: +{
+ "default": false,
+ "title": "Dry Run",
+ "type": "boolean"
+}execute_on_group2 fields changedInput schema / properties / dry_runAdded value: +{
+ "default": false,
+ "title": "Dry Run",
+ "type": "boolean"
+}Input schema / properties / forceAdded value: +{
+ "default": false,
+ "title": "Force",
+ "type": "boolean"
+}v0.1.0download_fileexecuteexecute_on_grouplist_groupslist_serversupload_fileEach tool has a clearly distinct purpose with no overlap: download_file and upload_file handle file transfers, execute and execute_on_group handle command execution on individual servers or groups, and list_groups and list_servers provide metadata. The descriptions reinforce these boundaries, making misselection unlikely.
All tools follow a consistent verb_noun pattern using snake_case: download_file, execute, execute_on_group, list_groups, list_servers, upload_file. This predictability aids agent comprehension and tool selection without deviation.
With 6 tools, the server is well-scoped for SSH/SFTP operations, covering core workflows like file transfer, command execution (individual and group), and server/group listing. Each tool earns its place without bloat or thin coverage.
The toolset provides strong coverage for basic SSH/SFTP tasks, including CRUD-like operations for files and commands. A minor gap exists in lifecycle management (e.g., no tools for creating/deleting servers or groups), but agents can work around this using execute for administrative commands.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.
Scoped, audited SSH exec, sessions, and SFTP on your saved servers without exposing credentials
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/blackaxgit/ssh-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
