Schema | ChatGPT SSH & SFTP MCP Server

ChatGPT SSH & SFTP MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_HOST`	No	HTTP listening address	127.0.0.1
`MCP_PORT`	No	HTTP listening port	8000
`MCP_TRANSPORT`	No	Transport protocol: http or stdio	http
`MCP_BEARER_TOKEN`	No	Optional HTTP bearer-token check; required for public deployments
`SSH_MCP_KEY_ROOT`	No	Directory allowed to contain SSH private keys	~/.ssh
`MCP_ALLOWED_HOSTS`	No	Additional allowed HTTP Host headers; required for public proxy hostname
`MCP_ALLOWED_ORIGINS`	No	Additional permitted HTTP Origin values
`SSH_MCP_KNOWN_HOSTS`	No	Verified SSH server host keys	~/.ssh/known_hosts
`SSH_MCP_SESSION_TTL`	No	Idle SSH connection expiry in seconds	1800
`SSH_MCP_MAX_SESSIONS`	No	Maximum simultaneous active SSH connections	32
`SSH_MCP_PROFILES_FILE`	No	Private JSON file for named server profiles
`SSH_MCP_TRANSFER_ROOT`	No	Confined local SFTP file exchange directory	./transfers
`SSH_MCP_MAX_INLINE_BYTES`	No	Maximum bytes per inline SFTP operation	1048576
`SSH_MCP_MAX_OUTPUT_BYTES`	No	Combined stdout/stderr limit per command	1048576
`SSH_MCP_MAX_COMMAND_SECONDS`	No	Maximum accepted SSH command timeout	120

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessNo issues