Skip to main content
Glama
mienetic

Ghostvault

by mienetic

Fill Input Field

gv_fill_input

Fills a form input by matching visible label text or CSS selector. Supports humanized typing with realistic cadence, typos, and configurable speed for anti-bot protected forms.

Instructions

Fill a form input on the current page.

Tries to find the input by its label text first (case-insensitive, substring match), falling back to a CSS selector.

By default this uses Playwright's instant paste (fast, but detectable). Set humanize=true to type one character at a time with a realistic log-normal cadence + optional typos — strongly recommended for Google login forms and any anti-bot-protected input.

Args: target: Visible label text of the field (preferred) OR a CSS selector. value: The text to type into the field. timeout_ms: Max wait time in ms (default 10000). humanize: Type char-by-char with realistic cadence. Defaults to the account's humanize_typing setting (off if unset). typing_speed_wpm: Target words-per-minute (40=slow, 90=avg, 150=fast). Defaults to the account's default_typing_wpm or 90. typing_variance: Cadence spread 0–1 (0=constant, 0.35=realistic, 1=erratic). Default 0.35. mistake_rate: Chance per char to typo-then-correct (0–0.05). Produces realistic Backspace events. Default 0 (off). delay_after_ms: Pause for a randomized ~this many ms after typing.

DECISION GUIDE — when to set humanize=true: • Google / SSO login forms (email, password) → ALWAYS (instant paste is the #1 bot detection tell) • Captcha-protected form fields → ALWAYS • Banking / payment forms → ALWAYS • 2FA / OTP code fields → optional (short codes, paste is fine) • Search boxes on trusted sites (Gmail, Drive) → optional • Quick one-off inputs in a familiar dashboard → can skip

Recommended values by scenario: • Login email: humanize=true, wpm=85, variance=0.4, mistakes=0.02 • Login password: humanize=true, wpm=65, variance=0.5, mistakes=0.0 • Long form: humanize=true, wpm=90, variance=0.35, mistakes=0.01 • Search box: humanize=false (or omit)

Note: If the account's humanize_policy is "always", humanize is forced on regardless of what you pass here.

Returns the target, char count, and whether humanize was applied.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
valueYes
targetYes
humanizeNo
timeout_msNo
mistake_rateNo
delay_after_msNo
typing_varianceNo
typing_speed_wpmNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

The description extensively discloses behavioral traits: instant paste vs humanize typing, account policy overrides, return values, and detectability. Annotations only provide openWorldHint, so the description carries the full burden and meets it excellently.

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

Conciseness4/5

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

The description is well-structured with sections for arguments, decision guide, and notes. It is somewhat lengthy but every section adds value. The front-loaded purpose and organized layout aid scanning.

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

Completeness5/5

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

Given the complexity (8 parameters, output schema exists), the description is complete. It covers all parameter semantics, usage context, behavioral details, and return values. No gaps are evident.

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

Parameters5/5

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

With 0% schema description coverage, the description fully explains all 8 parameters, including defaults, recommended values by scenario, and the effect of account-level settings. This adds significant meaning beyond the bare schema.

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

Purpose5/5

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

The description clearly states 'Fill a form input on the current page' with a specific verb and resource. It distinguishes itself from siblings like gv_click_element and gv_open_url by focusing on input field filling.

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?

While the description does not explicitly compare to alternatives, it provides clear context on how the tool finds inputs (label text then CSS selector) and includes a Decision Guide for when to set humanize=true. The implied use case is sufficiently clear for agents.

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

Install Server

Other Tools

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/mienetic/Ghostvault'

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