Skip to main content
Glama
DICloak Local API MCP Server

DICloak Local API MCP Server

Official

chrome_keyboard

Simulate keyboard events in a browser to type text, trigger shortcuts like Ctrl+C, or send special keys such as Enter and PageUp, optionally targeting a specific element first.

Instructions

Simulate keyboard events in the browser environment, optionally targeting a specific element. Supports single keys, combinations (e.g. Ctrl+C), and special keys (e.g. Enter, Tab, PageUp, PageDown, ArrowUp, ArrowDown, ArrowLeft, ArrowRight).For example, use the PageDown and PageUp keys to scroll the page down and up, respectively.For multiple keys in sequence, seperate them with a comma.

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": {
      "envId": "<envId>",
      "keys": "<keys>"
    },
    "name": "chrome_keyboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysYesKey sequence, supports combinations (e.g. Ctrl+C)
delayNoDelay between keys in ms
envIdYesEnvironment ID for the browser environment to operate.
selectorNoTarget element selector (optional) to focus before typing. If not provided, types to the active element or page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It says nothing about whether events are trusted or synthesized, whether they require page focus, what happens if the selector does not match, whether the call waits for completion, or what errors look like. The only behavioral disclosure is that it operates in 'the browser environment', which is already implied by the tool name and envId parameter.

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

Conciseness3/5

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

The core purpose is front-loaded in one sentence, which is good. The following sentences are somewhat run-on with missing whitespace before 'For example' and a typo ('seperate'), and the PageUp/PageDown example partially repeats the special-key list already given, so it is serviceable rather than tight.

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

Completeness3/5

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

For a 4-parameter, side-effecting browser tool with no annotations and no output schema, the description covers what it does and the accepted key syntax but omits behavior on failure, timing/delay semantics beyond the schema default, and any note about return values. It is adequate to call the tool, but not complete for reasoning about its effects.

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 100%, so the schema already documents keys, delay, envId, and selector, making 3 the baseline. The description earns above baseline by explaining the comma-separated syntax for sequential keys and by restating that the selector is optional and falls back to the active element, which the schema covers only tersely ('Key sequence, supports combinations').

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?

The description opens with a specific verb+resource pair: 'Simulate keyboard events in the browser environment.' It adds scope (optionally targeting an element) and supported key classes, which lets an agent separate it from chrome_click_element or chrome_mouse_control. It stops short of naming a sibling explicitly, so 4 rather than 5.

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?

Usage context is implied rather than stated: 'use the PageDown and PageUp keys to scroll the page down and up' is a concrete example of when to reach for this tool, and the comma syntax tells the agent how to chain keys. However, there is no explicit when-not guidance and no mention of alternatives such as chrome_click_element or chrome_fill_or_select for focused interactions.

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