Desarrollado en el Hackathon MCP de AGI House
Este proyecto es un agente de automatización de navegadores que utiliza el Protocolo de Contexto de Modelo (MCP) para habilitar las interacciones con el navegador. Proporciona una integración fluida entre Claude y las funciones de automatización de navegadores a través de nuestro servidor MCP.
¡Gracias a Browser-Use por sus capacidades de agente de navegador que ayudan a impulsar nuestro servidor MCP!
Related MCP server: selenium-mcp
macOS (darwin 24.2.0)
Python 3.12 o superior
administrador de paquetes uv
Navegador Google Chrome (asegúrese de que su navegador esté cerrado antes de ejecutar tareas).
Para instalar automáticamente el Agente de automatización del navegador para Claude Desktop a través de Smithery :
npx -y @smithery/cli install @ashley-ha/mcp-manus --client claudeClonar el repositorio:
git clone <repository-url>
cd mcpConfigurar el entorno de Python usando uv :
uv venv
source .venv/bin/activate
uv syncCree o modifique su archivo de configuración de Claude Desktop:
{
"mcpServers": {
"browser-use": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/mcp",
"run",
"browser-use.py"
]
}
}
}Reemplace /ABSOLUTE/PATH/TO/browser-use con la ruta absoluta al directorio de su proyecto.
El agente está configurado para utilizar Google Chrome con la siguiente configuración predeterminada:
Modo sin cabeza para desarrollo
Tamaño de la ventana: 1280x1100
Funciones de seguridad deshabilitadas para pruebas
Ruta de grabación: ./tmp/recordings
Automatización del navegador mediante herramientas MCP
Capacidades de gestión y planificación del Estado
Detección y manipulación de elementos interactivos
Contextos de navegador configurables
Soporte de registro y depuración
El agente proporciona dos herramientas principales:
get_planner_state : recupera el estado actual del navegador y el contexto de planificación
execute_actions : ejecuta acciones planificadas en el navegador
El proyecto utiliza el registro integrado de Python con la siguiente configuración:
Todos los registros se dirigen a stderr
Formato personalizado: %(levelname)-8s [%(name)s] %(message)s
Nivel de registrador raíz: INFO
Nivel de registradores de terceros: ADVERTENCIA
browser-use.py : Punto de entrada principal e implementación del servidor
tmp/recordings : Directorio para grabaciones de sesiones del navegador
Dependencias gestionadas a través de uv
Este proyecto se desarrolló durante el Hackathon MCP de AGI House. ¡Agradecemos cualquier contribución!
Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.
Derechos de autor (c) 2025 Jaeyun Ha, Ashley Ha
Por la presente se concede permiso, sin cargo, a cualquier persona que obtenga una copia de este software y los archivos de documentación asociados (el "Software"), para tratar el Software sin restricción, incluyendo, sin limitación, los derechos a usar, copiar, modificar, fusionar, publicar, distribuir, sublicenciar y/o vender copias del Software, y para permitir que las personas a quienes se les proporciona el Software lo hagan, sujeto a las siguientes condiciones:
El aviso de derechos de autor anterior y este aviso de permiso se incluirán en todas las copias o partes sustanciales del Software.
EL SOFTWARE SE PROPORCIONA "TAL CUAL", SIN GARANTÍA DE NINGÚN TIPO, EXPRESA O IMPLÍCITA, INCLUYENDO, ENTRE OTRAS, LAS GARANTÍAS DE COMERCIABILIDAD, IDONEIDAD PARA UN FIN DETERMINADO Y NO INFRACCIÓN. EN NINGÚN CASO LOS AUTORES O TITULARES DE LOS DERECHOS DE AUTOR SERÁN RESPONSABLES DE NINGUNA RECLAMACIÓN, DAÑOS U OTRAS RESPONSABILIDADES, YA SEA EN ACCIÓN CONTRACTUAL, EXTRACONTRACTUAL O DE OTRO TIPO, QUE SURJA DE, SE DERIVE DE O EN RELACIÓN CON EL SOFTWARE O EL USO U OTRAS RELACIONES CON EL MISMO.
Execute actions from the planner state.
Args:
actions: A dictionary containing the planner state and actions in format:
{
"current_state": {
"evaluation_previous_goal": str,
"memory": str,
"next_goal": str
},
"action": [
{"action_name": {"param1": "value1"}},
...
]
}
Note: If the page state changes (new elements appear) during action execution,
the sequence will be interrupted and you'll need to get a new planner state.
| Name | Required | Description | Default |
|---|---|---|---|
| actions | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that execution can be interrupted by page state changes, which is a key behavioral trait, but doesn't cover other aspects like error handling, side effects, or response format. It adds some context but is incomplete for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded with the main purpose, followed by an 'Args' section and a note. The structure is clear, but the note could be more integrated; overall, it's efficient with minimal waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (1 parameter with nested objects, no annotations, no output schema), the description covers the parameter structure well and includes a behavioral note. However, it lacks details on return values, error cases, and full usage context, making it adequate but with gaps for a tool that likely performs mutations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate. It provides a detailed example of the 'actions' parameter structure, including nested objects and keys like 'current_state' and 'action', which adds significant meaning beyond the schema's generic 'object' type. This effectively documents the parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool 'Execute actions from the planner state', which provides a verb ('Execute') and resource ('actions from the planner state'), but it's vague about what 'actions' specifically entail (e.g., UI interactions, API calls) and doesn't clearly distinguish from the sibling tool 'get_planner_state'. It's not tautological but lacks specificity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a note about interruption when 'the page state changes', which implies a usage context (e.g., web automation), but it doesn't explicitly state when to use this tool versus alternatives like 'get_planner_state' or provide prerequisites. The guidance is minimal and not comprehensive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the current browser state and planning context. This tool must be executed before execute_actions tool.
Must return a JSON string in the format:
{
"current_state": {
"evaluation_previous_goal": "Success|Failed|Unknown - Analysis of previous actions",
"memory": "Description of what has been done and what to remember",
"next_goal": "What needs to be done with the next immediate action"
},
"action": [
{"action_name": {"param1": "value1", ...}},
...
]
}
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: it's a read operation ('Get'), it returns specific structured data (a JSON string with defined format), and it has a prerequisite relationship with another tool. It doesn't cover aspects like error handling or performance, but for a zero-parameter tool with no annotations, this is reasonably comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose and usage guideline in the first two sentences, which is good. However, it includes a detailed JSON format specification that might be better suited for an output schema. While this adds value, it makes the description longer than necessary for conciseness, as the output details could be separated into structured data.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 0 parameters, no annotations, and no output schema, the description provides good contextual completeness. It explains the purpose, usage guidelines, and output format in detail. The only gap is the lack of an output schema, but the description compensates by specifying the return format explicitly, making it sufficient for the agent to understand how to use the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description doesn't need to add parameter information, and it doesn't attempt to, which is appropriate. No parameters are present to document, so this score reflects that the description doesn't introduce confusion or redundancy regarding inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get the current browser state and planning context.' It specifies the verb ('Get') and resource ('browser state and planning context'), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from its sibling tool 'execute_actions' beyond stating a prerequisite relationship, which is more about usage than purpose distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: 'This tool must be executed before execute_actions tool.' It clearly states when to use this tool (as a prerequisite for 'execute_actions') and implies an alternative (use 'execute_actions' after this). This is a strong, directive guideline that helps the agent understand the tool's role in the workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
execute_actionsget_planner_stateScored across 2 tools
The two tools have completely distinct purposes: get_planner_state retrieves browser state and planning context, while execute_actions performs actions based on that state. There is no overlap or ambiguity between these functions.
Both tools follow a consistent verb_noun pattern with clear action-oriented names (get_planner_state, execute_actions). The naming convention is uniform and predictable throughout the set.
With only 2 tools for a browser automation server, the surface feels severely limited. While the tools cover a basic planning-execution loop, typical browser automation requires more granular operations like navigation, element interaction, or content extraction.
The toolset provides only a high-level planning/execution abstraction without direct browser manipulation capabilities. There are significant gaps for common browser tasks like navigating to URLs, clicking elements, extracting text, or handling dialogs, which agents would need for robust automation.
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
AI-powered web automation. Navigate websites using AI agents for one page or a thousand
Autonomous cloud agent tasks: real browser + your tools, structured evidence-backed results.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
