Skip to main content
Glama

browser_flow

Orchestrates multi-step browser workflows with automatic evidence capture. Supports flow, chain, and batch modes for actions like open, click, type, assert, and scroll.

Instructions

多步浏览器流程编排工具(v1.9.5 起合并 browser_chain 和 browser_batch),按步骤依次执行 open/click/type/wait/assert/eval/screenshot/snapshot/scroll/hover/select/navigate/har/step/clearErrors 等操作,每步自动捕获证据(截图+快照)。step.type 与 step.action 互为别名,二者至少传一个。通过 mode 参数区分子模式:flow(默认,标准编排)/ chain(链式,每步检查 console+network 错误,等价于 browser_chain)/ batch(批量,受 maxSteps 限制,等价于 browser_batch)。与 validation_flow 的区别:browser_flow 侧重浏览器操作编排,支持更多浏览器原生操作(open/har/snapshot/scroll/hover/select 等);validation_flow 侧重验证语义,仅支持 navigate/click/type/wait/eval/screenshot 6 种操作。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo编排模式:flow(默认,标准多步编排)/ chain(链式,每步检查 console+network 错误,等价于已废弃的 browser_chain)/ batch(批量,受 maxSteps 限制,等价于已废弃的 browser_batch)flow
stepsYes流程步骤列表,按顺序执行。每个步骤的 type/action 字段互为别名,至少传一个。chain 模式下也可使用 actions 字段名(向后兼容 browser_chain)
actionsNochain 模式下 steps 的别名(向后兼容 browser_chain)。优先使用 steps 字段
maxStepsNobatch 模式专用:最大步骤数限制(默认 20)。超出则报错
clearErrorsNo流程开始前是否清空运行时错误日志,默认 true
stopOnErrorNochain 模式专用:某步骤失败后是否停止(默认 true)。等价于 continueOnError 的反义,stopOnError=true 等价于 continueOnError=false
includeConsoleNochain 模式专用:每步是否检查控制台错误(默认 true)
includeNetworkNochain 模式专用:每步是否检查网络错误(默认 true)
continueOnErrorNo某步骤失败后是否继续执行后续步骤,默认 false(失败即停止)。chain 模式下默认 false(等价于 stopOnError=true)
Behavior4/5

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

No annotations are provided, so the description fully bears the burden. It discloses automatic evidence capture (screenshot+snapshot) per step, the alias between type and action, mode-specific behaviors (chain checks console/network errors, batch limits steps), and the stop-on-error/continue-on-error options. While it does not cover auth requirements or session management, these are likely handled by other tools and the description provides adequate transparency for the core behavior.

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 concise (4-5 lines in Chinese), front-loaded with the core purpose, and well-structured: it states the tool function, lists operations, explains aliases, describes modes, and contrasts with a sibling. Every sentence adds value without redundancy.

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 tool with 9 parameters, nested steps, and no output schema, the description is fairly complete: it covers purpose, mode semantics, step aliases, and sibling differentiation. However, it does not describe the return value or specify the requirement for an active browser session (though implied by the sibling list). A minor gap reduces it from perfect.

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 description coverage is 100%, baseline is 3. The description adds value by explaining the overall workflow, the mode parameter's semantics (flow/chain/batch with deprecated tool equivalences), the type/action alias, and the auto-evidence capture. This contextual information goes beyond the schema's field-level descriptions.

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 it is a multi-step browser workflow orchestrator, lists supported operations, and explicitly distinguishes it from validation_flow by detailing the different focus and supported actions. The verb '编排' (orchestrate) and resource '浏览器流程' (browser flow) are specific, and the comparison with a sibling provides differentiation.

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 provides clear context on when to use browser_flow vs validation_flow, explains the mode parameter and its sub-modes (flow/chain/batch) with their equivalences to deprecated tools, and describes the type/action alias. It lacks an explicit 'when not to use' statement but the comparison effectively guides selection.

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/validpilot/ai-verify-mcp'

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