google-scholar-labs-ajg-mcp
Google Scholar Labs Search (Versión adaptada a MCP AJG 2024)
Servicio Model Context Protocol (MCP) para grandes modelos locales y agentes de IA (Agent). Recupera literatura académica de Google Scholar Labs aprovechando la sesión ya iniciada del navegador local del usuario, y filtra las revistas revisadas por pares siguiendo estrictamente el directorio de clasificación de revistas autorizado AJG 2024 (Academic Journal Guide / ABS).
Demostración offline de Dry-Run en la terminal

Related MCP server: Gemini Research MCP Server
Características principales
Filtrado estricto por clasificación de revistas AJG 2024: compara estrictamente las publicaciones (Venue) de la literatura recuperada con el directorio oficial AJG 2024 (de forma predeterminada ABS2+:
2,3,4,4*). Admite umbrales de estrellas personalizados y el filtrado por grandes áreas disciplinarias (comoFINANCE,ACCOUNT,STRAT,ECON,ORMAN, etc.).Registro transparente de exclusiones (Exclusion Transparency): las publicaciones que no cumplen las condiciones (como preprints de arXiv/SSRN, revistas no incluidas en AJG, estrellas por debajo del umbral o áreas disciplinarias sin coincidencia) quedan íntegramente registradas en
exclusionscon el motivo específico, lo que evita que publicaciones no esenciales se clasifiquen erróneamente como literatura válida.Salida completa de resultados válidos: devuelve todas las publicaciones de la página de resultados actual que cumplen las condiciones de clasificación, sin truncarlas artificialmente a las 3 primeras.
Transferencia segura con intervención humana (Human-in-the-Loop Handoff): ante la verificación de inicio de sesión de Google o un CAPTCHA, se pausa de inmediato de forma segura y devuelve
handoff_required: true; el usuario completa la verificación manualmente en la interfaz del navegador local. Nunca se intenta eludirla por la fuerza ni robar credenciales.Local primero y cero telemetría: se ejecuta por completo en el entorno local y se comunica mediante Stdio JSON-RPC 2.0 estándar, sin enviar credenciales ni historiales de búsqueda a servidores de terceros.
Núcleo de análisis sin dependencias externas: incluye un directorio central de revistas integrado y un analizador XLSX de biblioteca estándar pura, lo que permite ejecutar pruebas deterministas completas incluso en un CI o en entornos limpios sin archivos Excel externos.
Arquitectura y flujo de trabajo
[ AI 智能体 (Codex / Claude / Cursor / Windsurf) ]
│
(Stdio JSON-RPC 2.0)
▼
[ ScholarLabsMCPServer ]
│ │
│ (Dry-Run / Mock) │ (浏览器自动化模式)
▼ ▼
[ 快速 Schema 验证 ] [ CloakBrowser 会话 ]
│ (本地持久化 Profile)
▼
[ Google Scholar Labs ]
│ (HTML DOM 卡片提取)
▼
[ 候选论文卡片 ]
│
▼
[ AJG 2024 匹配引擎 ]
┌──────────┴──────────┐
▼ ▼
[ 合格文献列表 ] [ 剔除记录 ]
└──────────┬──────────┘
▼
[ 结构化 JSON 响应结果 ]Instalación y configuración
Requisitos del entorno
Python 3.10 o superior
(Opcional para ejecutar búsquedas automatizadas reales) biblioteca
cloakbrowsery entorno del navegador Chromium
1. Instalación desde el código fuente
git clone https://github.com/divenire990/Google-scholar-labs-ajg-mcp.git
cd Google-scholar-labs-ajg-mcp
pip install -e .Instale las dependencias de desarrollo y compilación:
pip install -e ".[dev]"
# 或者仅安装打包构建依赖:
pip install -e ".[build]"2. Compilación de paquetes de distribución (sdist & wheel)
Compile el paquete de distribución de código fuente (.tar.gz) y la Wheel binaria (.whl):
pip install build
python -m buildLos archivos generados por la compilación se encuentran en el directorio dist/ (ignorados automáticamente por .gitignore).
3. Configuración de variables de entorno (opcional)
Copie .env.example a .env o configure las variables de entorno en la terminal:
# 本地浏览器持久化 Profile 路径(保存 Google 登录态)
export SCHOLAR_LABS_BROWSER_PROFILE="$HOME/.scholar-labs/browser-profile"
# 自定义 AJG2024.xlsx 数据文件路径(未设置时自动使用内置核心期刊或 data/AJG2024.xlsx)
export AJG_DATA_PATH="/path/to/AJG2024.xlsx"Configuración del cliente MCP
Añada google-scholar-labs-ajg-mcp a la configuración de su cliente de IA:
Claude Desktop / Claude Code (claude_desktop_config.json)
{
"mcpServers": {
"google-scholar-labs-ajg-mcp": {
"command": "python",
"args": ["-m", "scholar_labs.mcp_server"],
"env": {
"SCHOLAR_LABS_BROWSER_PROFILE": "/path/to/your/browser-profile",
"AJG_DATA_PATH": "/path/to/AJG2024.xlsx"
}
}
}
}Codex / Windsurf / Cursor (mcp.json o .toml)
[mcp_servers.google_scholar_labs_ajg_mcp]
command = "python"
args = ["-m", "scholar_labs.mcp_server"]Descripción de la interfaz de la herramienta: scholar_labs_search
Parámetros de entrada
Parámetro | Tipo | Valor predeterminado | Descripción |
|
| (obligatorio) | Tema, pregunta o palabras clave de la búsqueda académica enviada a Google Scholar Labs. |
|
|
| Umbral mínimo de filtrado por estrellas AJG ( |
|
|
| Lista opcional de códigos de áreas disciplinarias (por ejemplo, |
|
|
| Número máximo de tarjetas candidatas extraídas en el primer análisis. |
|
|
| Indica si el navegador se ejecuta en modo sin interfaz (headless). |
|
|
| Ruta personalizada del directorio de perfil persistente (Profile) (anula la variable de entorno). |
|
|
| Modo dry-run: solo verifica la consulta y el motor de coincidencia con AJG, sin iniciar el navegador. |
|
|
| Contenido HTML simulado (Mock) para la evaluación y las pruebas sin conexión. |
Ejemplo de la respuesta de salida
{
"status": "ok | blocked | no_results | error",
"message": "执行结果摘要",
"query": "dynamic strategic deviation and earnings management",
"min_stars": "2",
"fields_filter": ["FINANCE", "ACCOUNT"],
"total_candidates_found": 8,
"qualified_count": 3,
"exclusion_count": 5,
"qualified_papers": [
{
"title": "Corporate Governance and Financial Reporting Quality",
"authors": "J Smith, A Taylor",
"year": 2022,
"venue": "Journal of Financial Economics",
"scholar_url": "https://doi.org/10.1016/j.jfineco.2022.01.001",
"annotation": "Investigates the causal link between strategic board adjustments and reporting accuracy.",
"citation_signal": "Cited by 142",
"position": 1,
"raw_text": "...",
"ajg_info": {
"official_title": "Journal of Financial Economics",
"ajg_star": "4*",
"field": "FINANCE",
"is_ft50": true,
"is_utd24": true,
"print_issn": "0304-405X"
},
"rank_score": 51.9
}
],
"exclusions": [
{
"title": "Machine Learning in Financial Forecasting",
"venue": "arXiv preprint arXiv:2104.01234",
"reason": "unmatched_venue",
"details": "Venue 'arXiv preprint' not found in AJG 2024 journal index",
"position": 3
}
],
"handoff_required": false,
"handoff_url": null
}Pruebas y verificación sin conexión
Ejecute las pruebas unitarias deterministas:
python -m unittest discover -s tests -p "test_*.py"Todas las pruebas se completan en menos de 2 segundos, sin dependencias de red ni de navegador.
Declaración de privacidad, seguridad y cumplimiento
Principio de transferencia segura y cero evasión: esta herramienta nunca intenta descifrar automáticamente los CAPTCHA de Google, ni recopila, exporta o transmite las contraseñas de las cuentas de Google del usuario. Cuando se encuentra un requisito de verificación, se pausa de inmediato y se solicita al usuario que la resuelva manualmente.
Aislamiento local de credenciales: todas las cookies y sesiones de inicio de sesión se guardan en el directorio de perfil (Profile) local especificado por el usuario, sin ningún tipo de sincronización remota.
Aviso de cumplimiento: Google Scholar Labs es un producto académico experimental de Google; los usuarios deben cumplir por su cuenta las condiciones del servicio de Google y las normas de búsqueda académica.
Atribución al proyecto original y licencia de código abierto
Este proyecto se publica bajo la Licencia MIT. Consulte el archivo LICENSE.
Agradecimientos de atribución
Este proyecto es una versión adaptada independiente que evoluciona y amplía el concepto del proyecto original Scholar Labs Search, con las siguientes incorporaciones:
Filtrado por clasificación de revistas académicas AJG 2024 (ABS) y ordenación ponderada
Mecanismo estructurado de clasificación de exclusiones (Exclusion Transparency)
Adaptación del protocolo estándar Model Context Protocol (MCP) JSON-RPC
Conjunto de pruebas deterministas sin conexión y arquitectura de transferencia segura
Available Tools
1 toolscholar_labs_searchA
Search Google Scholar Labs through a logged-in CloakBrowser session and filter results strictly against the AJG (Academic Journal Guide) 2024 rankings. Returns all qualifying papers (default ABS2+: 2, 3, 4, 4*) and detailed exclusion records for unmatchable or sub-threshold candidates. Supports manual handoff if CAPTCHA or Google login is required.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search topic, research question, or keyword query for Scholar Labs. | |
| fields | No | Optional list of AJG fields to filter journals (e.g. ['ACCOUNT', 'FINANCE', 'ECON', 'ORMAN', 'STRAT']). | |
| dry_run | No | If true, validates query and matcher setup without launching browser. | |
| headless | No | Run CloakBrowser in headless mode. Set to false if interactive takeover or visual inspection is desired. | |
| min_stars | No | Minimum AJG star rating required for qualification ('1', '2', '3', '4', '4*'). Default is '2' (ABS2+). | 2 |
| mock_html | No | Mock HTML content for non-network / offline testing and verification. | |
| profile_dir | No | Path to persistent browser profile directory (defaults to SCHOLAR_LABS_BROWSER_PROFILE or ~/.scholar-labs/browser-profile). | |
| ajg_data_path | No | Path to AJG2024.xlsx data file (defaults to AJG_DATA_PATH or data/AJG2024.xlsx). | |
| max_candidates | No | Maximum raw candidate cards to extract from the first visible Scholar Labs results page. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and largely succeeds: it discloses the logged-in-session requirement, the AJG strict-filtering behavior, and the CAPTCHA/manual-handoff scenario. It adds context beyond what structured fields offer, though it stops short of mentioning rate limits or failure modes beyond CAPTCHA. No contradiction with annotations exists since none are present.
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?
Three sentences, each earning its place: purpose, return behavior, and fallback handling. The primary purpose is front-loaded in sentence one. No filler or redundancy. Slightly more could be trimmed but it is appropriately tight for a tool of this complexity.
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?
For a complex browser-automation tool with 9 parameters, no output schema, and no annotations, the description covers the core workflow (search, AJG filtering, return of qualifying/excluded records) and the critical handoff path. It lacks an exact return-format spec, but the high-level return description partially compensates for the missing output schema.
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?
Schema description coverage is 100%, so all nine parameters are already documented in the schema with types, defaults, and descriptions. The tool description adds no additional parameter-level detail beyond restating the ABS2+ default that min_stars already encodes. Baseline 3 applies; the schema does the heavy lifting.
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 a specific verb and resource ('Search Google Scholar Labs through a logged-in CloakBrowser session') and adds the distinctive filtering behavior ('filter results strictly against the AJG 2024 rankings'). It also specifies the return scope (qualifying papers plus exclusion records). Clear, specific, and unambiguous even without siblings to differentiate.
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 states what the tool does and notes the manual-handoff path for CAPTCHA or login, which gives context on when a human may need to step in. However, with no sibling tools listed and no explicit when-to-use vs when-not-to-use statements, the usage guidance is implicit rather than directive. The handoff note is a behavioral fallback, not a usage-exclusion rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
scholar_labs_search
TDQS
Scored across 1 tool
With only a single tool, there is no possible confusion between competing choices. The tool's purpose is clear and distinct by default.
The name `scholar_labs_search` follows a consistent domain/action pattern. With only one tool, there are no naming conflicts or inconsistencies to evaluate.
A single tool is at the low end of the typical range, but it provides a comprehensive search-and-filter operation for a narrowly scoped server. It is slightly under the usual 3-15 tools yet reasonable for this focused purpose.
The tool covers the full search workflow including AJG filtering, exclusion records, and authentication/CAPTCHA handoff. Within the stated domain of AJG-filtered Google Scholar search, there are no obvious missing operations.
Maintenance
Related MCP Connectors
MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
Scrape, crawl and search the web for AI agents via MCP.
MCP server for Google search results via SERP API
Free web search for AI agents. No API key required. Hosted MCP in active development.
Related MCP Servers
- AlicenseBqualityDmaintenanceA local MCP server that allows users to search Google Scholar for academic papers by topic, author, and year range without requiring API keys. It utilizes web scraping to provide paginated results for research and academic exploration through natural language.2MIT
- AlicenseAqualityBmaintenanceMCP server for AI-powered research using Gemini. Provides fast grounded web search, deep autonomous research, URL extraction, and session management.627 PyPI9MIT
- AlicenseAqualityDmaintenanceMCP server for the OpenAlex scholarly database, providing AI agents with tools to search and retrieve academic works, authors, and institutions via natural language queries.8MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server for searching Google Scholar, enabling paper search, author lookup, citation tracking, and BibTeX export for AI assistants and automation workflows.48 PyPI2MIT