MCP Aseps
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP AsepsRemember that my project deadline is Friday"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Aseps — Modular Multi-Server Suite
Agnostik, modular MCP (Model Context Protocol) server suite untuk agent yang berbasis memori, pengetahuan, skill, dan integrasi eksternal. Dirancang untuk efisiensi token, local-first storage, dan mudah di-deploy di berbagai editor (Claude Desktop, Cline, Cursor, dll).
Fitur Utama
servers/orchestrator — MAF (Master Agentic Framework) Orchestrator untuk routing dan manajemen eksekusi agent.
servers/decision — SemIf (JEV-CPU) Decision Layer untuk triage, risk assessment, dan decision routing.
servers/core — filesystem, shell, system, web, dan security tools (OMP Runtime).
servers/memory — long-term memory (LTM) & Hindsight Engine dengan SQLite + sqlite-vec + FTS5 + Ollama embeddings.
servers/knowledge — workspace RAG: indexing file teks, chunking, hybrid semantic + keyword search.
servers/document — Document extraction, OCR vision text rendering, dan PDF processing.
servers/skills — procedural memory / skill registry dengan semantic recall.
servers/bridge — integrasi sistem eksternal: Gmail, Telegram, Gemini, Vision, MikroTik RouterOS (credential dari
.env).shared/ — konfigurasi terpusat, embedding client, Redis cache, model, logging, security.
config/ — konfigurasi editor universal (
mcp_universal.json,claude_desktop_config.json,cline_mcp_settings.json).scripts/ —
start-all.sh,stop-all.sh,backup.sh,start-omp.sh,setup-vscode.sh.
Related MCP server: VegaMCP
Prasyarat
Python 3.12+
Ollama (untuk embedding) — default
http://localhost:11434, modelnomic-embed-textRedis opsional — untuk embedding cache dan working memory
Docker + docker-compose opsional — untuk menjalankan Ollama & Redis
Instalasi Cepat
git clone https://github.com/asepsafrudin/multiple-mcp-server-by-kimi.git /home/aseps/MCP
cd /home/aseps/MCP
cp .env.example .env
# edit .env sesuai environment Anda
make installMenjalankan Server
Mode SSE (background, untuk testing/remote)
make start
# Akses endpoint: http://127.0.0.1:8000/sse (core), 8001 (memory), dst.
make stopMode stdio (untuk integrasi editor)
Gunakan file konfigurasi di config/:
config/claude_desktop_config.jsonconfig/cline_mcp_settings.jsonconfig/mcp_universal.json
Salin konfigurasi yang sesuai ke editor Anda.
Struktur Direktori
.
├── config/ # konfigurasi editor & universal
├── data/ # SQLite databases (memory_v2.db, knowledge_v2.db, skills_v2.db)
├── servers/
│ ├── orchestrator/ # MAF Orchestrator (Tugas / Routing)
│ ├── decision/ # SemIf (JEV-CPU) Decision layer
│ ├── core/
│ ├── memory/ # Memory (LTM) & Hindsight Engine
│ ├── knowledge/
│ ├── document/ # Document & PDF OCR extraction
│ ├── skills/
│ └── bridge/
├── shared/ # library bersama
├── scripts/ # start-all, stop-all, backup, OMP & vscode scripts
├── tasks/ # daftar tugas dan progress implementasi
├── tests/ # pytest suite
├── workspace/ # symlink bekerja (sandboxing environment)
├── docker-compose.yml
├── Makefile
├── pyproject.toml
└── .env.examplePerintah Makefile
make install # buat venv & install editable + dev deps
make dev # install editable
make test # jalankan pytest
make lint # ruff check
make format # ruff format & auto-fix
make clean # bersihkan cache
make start # start semua server SSE
make stop # stop semua server
make backup # backup SQLite databasesCI/CD Status
GitHub Actions workflows aktif di repo ini:
ci.yml— menjalankan pytest + ruff + mypy pada setiap push kemaindan setiap PRlint.yml— fast lane: hanya ruff (untuk feedback cepat)typecheck.yml— slow lane: mypy --strict harian (nightly cron)
Dokumentasi Detail
ARCHITECTURE.md — arsitektur & data flow
MEMORY.md — konsep dan penggunaan memory
KNOWLEDGE.md — workspace RAG
SKILLS.md — skill registry / procedural memory
SECURITY.md — keamanan & credentials
DEPLOYMENT.md — deployment & editor integration
ROADMAP.md — rencana pengembangan
TASKS.md — daftar tugas & status
Lisensi
MIT — lihat LICENSE untuk detail lengkap.
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP server and Agent Skills for specs, engineering threads, and project memory.
MCP server for building and testing AI agents with multi-model experimentation and insights.
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceA sophisticated MCP server providing advanced memory capabilities with RAG, hallucination detection, and enterprise-grade AI infrastructure for intelligent agent ecosystems.-
- AlicenseCqualityDmaintenanceA production-grade MCP server providing an autonomous AI agent swarm, persistent semantic memory, browser automation, multi-model reasoning, and 78+ tools for AI-first testing and development.63MIT
- AlicenseCqualityBmaintenanceAn MCP server offering hybrid memory recall and continuity tools for AI agents. It also provides a governance gateway that pre-approves risky shell/file/git actions before execution.19Apache 2.0
- AlicenseNot gradedqualityCmaintenanceA production-ready MCP server suite for AI agent tool integration, providing five composable tool modules: code analysis, web scraping, file operations, API integration, and data transformation.13 npmBSD 3-Clause