Skip to main content
Glama
surfskyio

surfsky-mcp

Official
by surfskyio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Act on the page

surfsky_act
Destructive

Perform human-like mouse and keyboard actions on the active tab: click, fill, type, press, select, scroll. Returns updated page state and snapshot to verify changes and continue browsing.

Instructions

Perform one input action on the active tab with human-like mouse and keyboard, then settle and return the page state (url, navigated, changed) plus a fresh snapshot with @N refs. Use it for every click, form entry and keypress. Per action: click, dblclick, hover take target; fill takes target and text and replaces the value; type takes target and text and appends keystrokes (target '@focused' types into the focused element without clicking); press takes key; select takes target and value; scroll takes target (scrolls it into view) or delta_y, and with neither scrolls most of a screen down. changed: false in the result means nothing observable happened: snapshot or wait instead of repeating the action. Actions hit the live site and submissions have real side effects: stop before a payment or final confirmation the user did not ask for.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoKey for press: a name such as Enter, Tab, Escape, Backspace, ArrowDown, or a combination like Control+A.
textNoText for fill (replaces the field's value) or type (keystrokes appended to it).
valueNoOption to choose for select: its value attribute, or its visible label with by_label.
actionYesclick, dblclick, hover (target); fill (target, text); type (target, text); press (key); select (target, value); scroll (target, or delta_y, or neither).
targetNoA CSS selector, @N from the latest snapshot of this tab, or text=words (the first visible element whose name contains the words). XPath is not accepted.
delta_yNoPixels to scroll the page for scroll without target: positive down, negative up. Default: most of a screen down.
timeoutNoSeconds allowed for the action, including finding the element (default 10).
by_labelNoMatch value against the option's visible label instead of its value attribute.
snapshotNoInclude a fresh snapshot of interactive elements in the result (default true).
modifiersNoModifier keys held during click, dblclick or press.
session_idNoSession from surfsky_session_start. Omit for the shared default session, started on first use.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.1

TDQS

A4.8/5.0
Behavior5/5

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

The description goes well beyond the annotations: it reveals that actions hit the live site, that submissions have real side effects, that the tool settles after acting, and that changed: false means nothing observable happened. It also explains that the result contains a fresh snapshot with @N refs, which is behaviorally important and not present in the annotations.

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 dense but purposeful, front-loading the tool's purpose and return value before enumerating action-specific rules. It contains no filler, though the action-by-action list partially overlaps with the input schema's action enum description, so the overall length is a bit high but justified.

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?

For a complex, destructive, live-action tool with 11 parameters and no output schema, the description covers all essential context: what each action does, how targets work, what the result contains, how to interpret changed: false, and when to stop. Nothing important seems missing for an agent to invoke it safely and correctly.

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 baseline is 3, but the description adds genuinely useful action-specific semantics: fill replaces the value, type appends keystrokes, '@focused' types into the focused element without clicking, and scroll with neither target nor delta_y scrolls most of a screen down. This clarifies combinations that the schema alone does not fully express.

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 states a specific verb and resource: perform one input action on the active tab with human-like mouse and keyboard, then settle and return page state plus a snapshot. It enumerates the exact actions (click, dblclick, hover, fill, type, press, select, scroll), making it unambiguous and distinguishable from the sibling navigation, read, screenshot, and wait tools.

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

Usage Guidelines5/5

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

It explicitly says to use the tool for every click, form entry, and keypress, and it tells the agent what to do when changed is false: take a snapshot or wait instead of repeating the action. It also gives a critical boundary: stop before payments or final confirmations the user did not ask for, which is a clear when-not-to-use instruction.

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

Deploy Server

Other Tools