Skip to main content
Glama

ssh

Execute commands on remote servers via SSH with support for password, key-based authentication, and bastion host connections through ProxyJump.

Instructions

Execute commands on a remote server via SSH. Supports password and key-based authentication. SSH agent is used as fallback on Unix. Sessions are automatically pooled and reused for the same host:port:user combination. Idle sessions expire after 10 minutes. Supports IPv6 addresses and ProxyJump (jump_host) for reaching servers through bastion hosts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hostYesSSH server hostname or IP address (IPv4 or IPv6),required
portNoSSH port number. Default: 22
userYesSSH username,required
passwordNoPassword for authentication
key_fileNoPath to SSH private key file (e.g. ~/.ssh/id_rsa)
passphraseNoPassphrase for encrypted private key
use_agentNoUse SSH agent for authentication. Default: true if no other auth method specified
commandNoCommand to execute on the remote server
disconnectNoClose the SSH session for this host (no command needed)
host_key_checkNoHost key verification: strict (requires known_hosts), tofu (trust on first use, default), none (insecure)
timeout_secNoCommand execution timeout in seconds. Default: 30, Max: 300
jump_hostNoJump/bastion host for ProxyJump (hostname or IP). When set, connects through this host to reach the target
jump_portNoJump host SSH port. Default: 22
jump_userNoJump host username. Default: same as user
jump_passwordNoJump host password. Default: same as password
jump_key_fileNoJump host SSH private key file. Default: same as key_file
jump_passphraseNoJump host key passphrase. Default: same as passphrase
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, yet description comprehensively covers session pooling/reuse logic, 10-minute idle expiration, Unix-specific agent fallback, and authentication hierarchy. Discloses critical runtime behavior (connection reuse) not inferable from schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five sentences with zero waste. Front-loaded with core purpose (sentence 1), followed by authentication (2), session lifecycle (3-4), and network capabilities (5). Each sentence introduces distinct operational knowledge.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Comprehensive for a 17-parameter tool with complex auth and networking. Covers auth mechanisms, session management, and ProxyJump patterns. No output schema exists; while it could describe command output format, the behavioral coverage is sufficient for agent selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage (baseline 3). Description adds semantic grouping for authentication methods (password/key/agent) and explains the jump_host ecosystem via ProxyJump context. References session pooling to justify the 'disconnect' parameter's purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with specific verb 'Execute' + resource 'commands on a remote server' + method 'via SSH'. Clearly distinguishes from sibling tools like 'bash' (local execution) and 'sftp' (file transfer) by specifying remote command execution scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context (remote server execution) and identifies specific scenarios (ProxyJump for bastion hosts, IPv6). Lacks explicit 'when not to use' comparisons to siblings like sftp, but the remote vs local distinction is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

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/knewstimek/agent-tool'

If you have feedback or need assistance with the MCP directory API, please join our Discord server