ARL-DMS MCP Server
ARL-DMS MCP Server
Expone el sistema de gestión documental (DMS) de AKIJ Resources a los clientes MCP (opencode, Claude, etc.) a través de stdio JSON-RPC 2.0.
Fuentes servidas
# | Fuente | Tipo | Contenido |
1 | ERP (DWH) | MSSQL | Solo lectura por diseño (consultado vía AkijMCP, no aquí) |
2 | Risk database | PostgreSQL (Azure) | 8,288 riesgos / 16 categorías / 198 SBUs / 8,288 controles |
3 | One Goal One Team (Drive root) | Google Drive | 1,124 archivos / 187 carpetas |
4 | Risk Team - All Policies and SOP | Google Drive | 244 documentos (enlaces proporcionados por el usuario) |
5 | Legal Data | Google Drive | 686 archivos / 235 carpetas |
6 | Land | Google Drive | 210 archivos / 50 carpetas |
7 | ESG MLOD SSOT sheets | Google Sheets | 11,636 enlaces de SSOT 1 (+ SSOT 2/3 parcial) |
8 | SBU submission sheets | Google Sheets | 127 enlaces (5 de 32 hojas públicas; las demás privadas/401) |
9 | Bangladesh Laws (BDLaws portal) | Links | 20 leyes empresariales/corporativas básicas |
Índice: 14,535 entradas (12,786 archivos / 1,749 carpetas) en
~/.agents/skills/ARL-DMS/library/tree.json.
Related MCP server: google-drive-rag-mcp
Herramientas
dms_search(query, source?, limit)— busca documentos en todos los repositoriosdms_list(source?, limit)— lista archivos de un repositoriodms_details(id | name)— tarjeta de detalles + mapeo de cumplimiento de 3 nivelesdms_fetch(id, name?)— obtiene el texto del documento desde Drive públicodms_risk_lookup(query?, category?, sbu?, limit)— registro de riesgos PostgreSQL en vivodms_bdlaws_act(name?)— enlace oficial de bdlaws + metadatos de las 20 leyesdms_stats()— estadísticas del inventario
Ejecución
node server-arl-dms.jsVariables de entorno (se pueden sobrescribir mediante el bloque de entorno del servidor MCP):
RISK_PG_HOST/RISK_PG_PORT/RISK_PG_DATABASE/RISK_PG_USER/RISK_PG_PASSWORD— registro de riesgos PostgreSQLARL_DMS_SKILL_DIR— ruta a la biblioteca de skills de ARL-DMS (por defecto,~/.agents/skills/ARL-DMS)ARL_DMS_TREE_PATH/ARL_DMS_CONFIG_PATH— rutas explícitas de índice/configuración
Registro (opencode)
"ARL-DMS": {
"type": "local",
"command": ["node", "/Users/humaninside/Desktop/ESG_SUS_Agents_Skills_MCPs/MCPs/arl-dms/server-arl-dms.js"],
"enabled": true,
"environment": {
"RISK_PG_HOST": "...", "RISK_PG_PORT": "5432",
"RISK_PG_DATABASE": "risk_register",
"RISK_PG_USER": "...", "RISK_PG_PASSWORD": "...",
"ARL_DMS_SKILL_DIR": "/Users/humaninside/.agents/skills/ARL-DMS"
}
}Notas
Solo lectura por diseño. Nunca escribe en ERP (DWH) ni en PostgreSQL.
28 hojas SBU privadas (401) aún no están indexadas — compártelas como "cualquier persona con el enlace puede ver" y vuelve a ejecutar la extracción de las hojas.
Las credenciales se proporcionan mediante el bloque de entorno de MCP, no en la configuración de la skill.
Available Tools
13 toolsdms_bdlaws_actA
Return the official Bangladesh law link and metadata for the 20 registered core business/corporate acts (Companies Act, Labour Act, VAT Act, etc.) from bdlaws.minlaw.gov.bd.
Inputs: name.
dms_detailsA
Get a details card for one document by drive id or name: name, id, URL, path, doc type, source, and the 3-tier compliance mapping scaffold.
Inputs: id, name.
dms_fetchA
Fetch the text content of a publicly shared Google Drive document (docx/gdoc/xlsx/gslides/pdf attempts) by drive id. Returns up to 20k chars.
Inputs: id (required), name.
dms_legal_controlsB
Query the Compliance Control Library (63 controls) from the Legal Compliance Workbook: control description, category, P/D/C, effectiveness, test method.
Inputs: limit, compliance_id.
dms_legal_documentsB
Query the Documents & Records Register (63 records) from the Legal Compliance Workbook: required evidence, retention, storage, evidence class.
Inputs: limit, compliance_id.
dms_legal_kpiA
Return compliance KPI/KRI definitions and Lookups (master data) from the Legal Compliance Workbook.
Inputs: no named parameters.
dms_legal_registerA
Query the AKIJ Bangladesh Legal Universe (80 instruments) from the Legal Compliance Master Workbook: laws, domains, instrument type, regulator, official source URL.
Inputs: limit, query, domain, instrument_type.
dms_legal_requirementC
Query the Master Compliance Register (63 requirements, 119 fields) from the Legal Compliance Workbook: legal basis, obligation, applicability, owner, risk, evidence, compliance status.
Inputs: id, limit, query.
dms_legal_riskB
Query the Compliance Risk Register (63 risks) from the Legal Compliance Workbook: risk statement, likelihood/impact, inherent/residual score, rating, owner, treatment.
Inputs: sbu, limit, query, min_rating.
dms_listA
List documents in a DMS source repository (drive, risk-team, legal-data, land, sheet, bdlaws) with id, path, doc type and url.
Inputs: limit, source.
dms_risk_lookupA
Query the Bangladesh legal/compliance risk register (PostgreSQL, 8,288 risks) by keyword, category, or SBU. Returns risk code, title, scores, ratings, status.
Inputs: sbu, limit, query, category.
dms_searchA
Search the ARL-DMS document library (14,535 indexed files across Drive root, Risk Team, Legal Data, Land, ESG sheets, SBU sheets, and BD Laws). Returns matching documents with name, path, drive id, url, doc type and source.
Inputs: query (required), limit, source.
dms_statsA
Return DMS inventory statistics: total files/folders, counts by source and document type, registered sources, BD laws count.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Each tool targets a distinct entity or action: document search vs. listing vs. details vs. fetch, plus separate registers for risks, controls, requirements, etc. The descriptions clearly differentiate them.
All tools use lowercase with underscores and the 'dms_' prefix. Some are verb-based (search, list, fetch) while others are noun-based (details, stats), showing minor inconsistency but overall predictable.
13 tools cover both document management and legal compliance without being overwhelming. Each tool serves a clear purpose, well-scoped for the server's domain.
The tool set covers searching, listing, retrieving documents, and querying multiple legal/compliance registers (risks, controls, requirements, documents). No obvious gaps for a read-only compliance DMS.
Maintenance
Related MCP Connectors
Read-only MCP server over the developer docs for the portfolio's JSON API, MCP, A2A and NLWeb.
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for indexing, semantic search, and generation of multi-format documents. Exposes 13 tools over JSON-RPC 2.0 so an LLM can search your local PDF, Excel, and Word files, and create or edit Excel and Word documents.AGPL 3.0
- AlicenseAqualityDmaintenanceA local MCP server that enables LLMs to securely search and read files within designated Google Drive folders. Supports Google Docs, Google Sheets, PDFs, and plain text with strict folder-scoping via service account authentication.4MIT
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server that exposes a configured Google Drive folder to MCP clients, enabling them to list, search, and extract content from various file formats like Excel, CSV, PDF, DOCX, and images.ISC
- FlicenseBqualityCmaintenanceEnables any MCP-compatible client to perform filesystem operations — reading, listing, writing, searching, watching directories, and batch processing files — over JSON-RPC 2.0 stdio transport. Includes resource discovery, metrics tracking, and security controls such as allowed roots, size limits, and format allowlists, with a LangGraph agent that accesses files exclusively through MCP.6-