kt-mcp

Overview Schema Source Related Servers Discussions Admin

bash

Execute shell commands in the workspace without a sandbox, with configurable timeouts up to 300 seconds and background job polling for long-running tasks.

Instructions

Run Bash in the workspace. No sandbox. timeout defaults to 60 seconds (maximum 300). run_in_background returns a job_id; poll job_status/job_wait. Output is bounded.

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": {
      "command": "<command>"
    },
    "name": "bash"
  }
}

Input Schema

Name	Required	Description	Default
`command`	Yes
`timeout`	No
`run_in_background`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 2, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description adds substantial context beyond that: no sandbox (a significant safety disclosure), a bounded output cap, the 60s default / 300s ceiling, and that background runs yield a job_id. Missing are failure semantics (exit codes, stderr, what happens on timeout).

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?

Four short clauses, front-loaded with the highest-stakes fact (no sandbox), with no filler. Timeout constraints and background semantics are packed into the minimum space.

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?

For a three-parameter tool with no output schema, the description covers the essentials an agent needs before invoking: execution context, time limits, async flow, and output bounding. It stops short of describing error/exit-code reporting and working-directory behavior.

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 coverage is 0%, so the description must carry the load, and it does for two of three parameters: timeout (default 60, max 300, matching the schema) and run_in_background (returns a job_id for polling). The command parameter's expected form (single string, multi-line, shell chaining) is left unstated.

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?

"Run Bash in the workspace" states a specific verb and resource, and "No sandbox" adds a meaningful qualifier. It does not distinguish itself from siblings like python or grep/read, which are plausible substitutes, so an agent must infer the boundary itself.

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

Usage Guidelines3/5

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

It gives real routing guidance for the background case — poll job_status/job_wait — which is useful. But it never says when to prefer bash over python or the dedicated file/search tools, nor when not to use it (e.g., for file edits that edit/multi_edit handle more safely).

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

Deploy Server