Skip to main content
Glama
amol21p

mcp-interactive-terminal

by amol21p

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_TERMINAL_SANDBOXNoEnable OS-level kernel sandboxingfalse
MCP_TERMINAL_AUDIT_LOGNoPath to JSON audit log file
MCP_TERMINAL_LOG_INPUTSNoLog all inputs to stderr (for debugging)false
MCP_TERMINAL_MAX_OUTPUTNoMax output chars per read20000
MCP_TERMINAL_IDLE_TIMEOUTNoAuto-close idle sessions (ms, default 30min, 0 = disabled)1800000
MCP_TERMINAL_MAX_SESSIONSNoMax concurrent sessions10
MCP_TERMINAL_ALLOWED_PATHSNoComma-separated paths sessions can access
MCP_TERMINAL_REDACT_SECRETSNoRedact AWS keys, tokens, private keys in outputfalse
MCP_TERMINAL_DEFAULT_TIMEOUTNoDefault wait timeout (ms)5000
MCP_TERMINAL_ALLOWED_COMMANDSNoComma-separated allowlist (if set, only these are allowed)
MCP_TERMINAL_BLOCKED_COMMANDSNoComma-separated blocklist
MCP_TERMINAL_DANGER_DETECTIONNoEnable dangerous command confirmation flowtrue
MCP_TERMINAL_SANDBOX_ALLOW_WRITENoWritable paths in sandbox mode/tmp
MCP_TERMINAL_SANDBOX_ALLOW_NETWORKNoAllowed network domains in sandbox*

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
create_sessionA

Spawn an interactive terminal session (REPL, shell, database client, SSH, etc.). Returns a session_id for subsequent commands.

send_commandA

Send a command/input to an interactive session and wait for output. Appends newline automatically. Returns clean text output (no ANSI codes). If a dangerous command is detected, you must use confirm_dangerous_command first.

read_outputA

Read the current terminal screen without sending any input. Safe read-only operation.

list_sessionsA

List all active interactive terminal sessions. Safe read-only operation.

close_sessionB

Close/kill an interactive terminal session.

send_controlA

Send a control character or special key to a session (e.g., ctrl+c to interrupt, ctrl+d to send EOF, arrow keys, tab for completion).

confirm_dangerous_commandA

Execute a command that was flagged as dangerous by send_command. Requires a justification explaining WHY the command is necessary. This is a separate confirmation step for safety.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/amol21p/mcp-interactive-terminal'

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