jev-ultrafast-mcp

browser_act

Execute browser actions like clicks, typing, navigation, and verification in one call, batching multiple ops for efficient automation.

Instructions

Execute one or more ops in order, then return a delta observation.

Batch ops into a single call — each call is a round trip.

op fields click ref (ref may be "e12", or "e12" of a combobox to open it) type ref, text, [clear=true], [submit=false] select ref, value (option value or label) toggle ref, [state] (checkbox/radio/switch; no state = flip) hover ref upload ref, path | paths[] keys key ("Enter", "Meta+A", "ArrowDown") | keys[] scroll [dir=down|up|left|right], [amount=600], [ref] nav url back | forward | reload wait [ms=500] wait_for_ref ref, [timeout_ms=8000] wait_for_text text, [timeout_ms=8000] wait_for_load [timeout_ms=20000] screenshot [path], [full=false], [format=jpeg] (path names a file in the shots dir) tab action=list|new|switch|close, [index], [url] eval js (only when JEVMCP_ALLOW_JS=1)

Actions matching the confirmation rules (pay, delete account, …) return needs_confirmation; re-send that op with "confirm": true to proceed. That covers every op that clicks, not only the one named click -- toggle presses the control too -- and the role it gates on is read from the element the server observed, never from the op.

A bare single character in keys is text, not a key press -- it goes into whatever has focus -- so it is refused (blocked_by_policy) on a field whose value must not leave the page rather than confirmed. Use type with that field's ref, which asks for "confirm": true and records {{secret}}.

Input Schema

TableJSON Schema

Name	Required	Default
`ops`	Yes
`dry_run`	No
`session`	No	default
`observe_after`	No
`stop_on_error`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.5Sep 25, 2026

TDQS

A4.4/5.0

Behavior5/5

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

The description goes far beyond the annotations by explaining confirmation behavior, covering ops beyond `click` that press controls, reading the role from the observed element rather than the op, and the `keys` single-character policy for sensitive fields. It also discloses environment-dependent behavior (`eval` only when JEVMALLOW_JS=1) and screenshot file conventions. This is rich behavioral context with no contradiction against 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.

Conciseness5/5

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

The description is dense but fully structured: a one-sentence purpose, a one-line batching rule, a tabular op reference, and focused prose for confirmation and key-handling edge cases. No sentence is filler, and the most important operational guidance is front-loaded.

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 tool's complexity, this description is unusually complete: it covers all op kinds, their parameters, default values, confirmation semantics, sensitive-field behavior, environment-gated features, and output style. The presence of an output schema covers the return shape, and the annotations already declare the safety profile, so nothing essential is missing for correct invocation.

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?

With 0% schema description coverage, the description carries nearly the entire semantic burden, and it does so well for the required `ops` array by documenting every op and its fields, defaults, and special values. It does not explain the optional top-level parameters (`dry_run`, `session`, `observe_after`, `stop_on_error`), although their names and defaults make their meaning reasonably inferable.

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 clear verb and resource: 'Execute one or more ops in order, then return a delta observation.' It also lists the supported operation types in a compact table, making the tool's scope obvious. It does not explicitly distinguish itself from siblings like browser_macro, which could plausibly also execute sequences of actions, so it misses the top score.

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?

The description gives explicit practical guidance: 'Batch ops into a single call — each call is a round trip,' which tells agents to consolidate actions to reduce latency. It also explains how to handle confirmation-requiring actions and how to properly enter text into protected fields. It does not state when to prefer an alternative sibling tool such as browser_macro or browser_goal.

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

Deploy Server