Skip to main content
Glama
network-terminal-mcp

network-terminal-mcp

by evgenyzh

terminal_write

Writes input to an active terminal session, appending a line terminator unless disabled, so AI agents can send commands to network devices over SSH, Telnet, TCP console, or serial.

Instructions

Write input, appending a line terminator unless enter=false.

Input is audited after known-secret redaction; use terminal_write_secret for passwords. Timeout fails the session and may mean a partial write.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session_id": "<session_id>",
      "data": "<data>"
    },
    "name": "terminal_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYes
enterNo
session_idYes

Output Schema

NameRequiredDescriptionDefault
okYes
stateNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.5.0
    • removedOutput schema / description
      Removed value: -"Result of writing raw input to a session.\n\nThe written text is recorded in the audit but deliberately not echoed\nback to the model, so repetitive input does not inflate the context."
    • removedOutput schema / properties / bytes_sent
      Removed value: -{
      -  "title": "Bytes Sent",
      -  "type": "integer"
      -}
    • addedOutput schema / properties / ok
      Added value: +{
      +  "title": "Ok",
      +  "type": "boolean"
      +}
    • removedOutput schema / properties / session_id
      Removed value: -{
      -  "title": "Session Id",
      -  "type": "string"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "session_id",
      -  "bytes_sent",
      -  "state"
      -]New value: +[
      +  "ok"
      +]
    • changedOutput schema / title
      Previous value: -"TerminalWriteResult"New value: +"WriteReply"
  2. Changed4 schema fields changedv0.2.1
    • addedInput schema / additionalProperties
      Added value: +false
    • changedOutput schema / description
      Previous value: -"Result of writing raw input to a session."New value: +"Result of writing raw input to a session.\n\nThe written text is recorded in the audit but deliberately not echoed\nback to the model, so repetitive input does not inflate the context."
    • removedOutput schema / properties / data
      Removed value: -{
      -  "title": "Data",
      -  "type": "string"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "session_id",
      -  "data",
      -  "bytes_sent",
      -  "state"
      -]New value: +[
      +  "session_id",
      +  "bytes_sent",
      +  "state"
      +]
  3. First observedv0.1.1

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavior: input is audited after known-secret redaction, and a timeout fails the session and may leave a partial write. That is meaningful operational context an agent could not infer otherwise. It does not say whether the call blocks awaiting echo or how the session degrades after a failure.

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?

Two tight sentences, no filler: the primary behavior comes first, followed by the security exception and the failure mode. Every clause carries distinct information.

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?

An output schema exists, so return values need not be explained, and the description covers the key behavioral risks of writing to a live session. The remaining gap is session lifecycle context — how this interacts with terminal_read and open_session/close_session — which an agent must infer from sibling names.

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

Parameters3/5

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

Schema description coverage is 0% across three parameters, so the description must compensate. It fully explains 'enter' (line terminator appended by default) and gives context for 'data' (subject to redaction), but 'session_id' is never described and it is unclear whether a wrong or stale ID errors or silently fails.

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

Purpose4/5

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

Names a specific verb and effect ('Write input, appending a line terminator unless enter=false'), which tells an agent exactly what a call does to a live session. The resource is implicit (a terminal session, inferred from session_id) rather than stated, and differentiation from siblings is only partial — terminal_write_secret is named but terminal_read is not distinguished.

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?

Explicitly routes sensitive input away from this tool: 'use terminal_write_secret for passwords' is a concrete when-not condition naming the alternative sibling. It lacks guidance on when to write versus read or how this relates to open_session/close_session, but the most dangerous misuse case is covered.

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