MCP Aseps
A modular MCP server suite that provides core tools, long-term memory, knowledge RAG, skills registry, and external integrations for AI agents.
README
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/core — filesystem, shell, system, web, dan security tools.
- servers/memory — long-term memory (LTM) dengan SQLite + sqlite-vec + FTS5 + Ollama embeddings.
- servers/knowledge — workspace RAG: indexing file teks, chunking, hybrid semantic + keyword search.
- servers/skills — procedural memory / skill registry dengan semantic recall.
- servers/bridge — integrasi Gmail, Telegram, Gemini, Vision OCR (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.
Prasyarat
- Python 3.12+
- Ollama (untuk embedding) — default
http://localhost:11434, modelnomic-embed-text - Redis 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 install
Menjalankan Server
Mode SSE (background, untuk testing/remote)
make start
# Akses endpoint: http://127.0.0.1:8000/sse (core), 8001 (memory), dst.
make stop
Mode 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/
│ ├── core/
│ ├── memory/
│ ├── knowledge/
│ ├── skills/
│ └── bridge/
├── shared/ # library bersama
├── scripts/ # start-all, stop-all, backup
├── tests/ # pytest suite
├── docker-compose.yml
├── Makefile
├── pyproject.toml
└── .env.example
Perintah 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 databases
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 jika tersedia.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.