🎓 Academic Proposal MCP Server

git clone https://github.com/ranoes/academic-mcp-proposal.git
cd academic-mcp-proposal
docker build -t academic-proposal-mcp:latest .

{
  "mcpServers": {
    "academic-proposal-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        ".:/workspace",
        "academic-proposal-mcp:latest"
      ]
    }
  }
}

# Clone the repository
git clone https://github.com/ranoes/academic-mcp-proposal.git
cd academic-mcp-proposal

# Install dependencies and package
pip install -e .
python server.py

{
  "mcpServers": {
    "academic-proposal-mcp": {
      "command": "python",
      "args": ["${workspaceFolder}/server.py"],
      "env": {
        "WORKSPACE_DIR": "${workspaceFolder}"
      }
    }
  }
}

{
  "metadata": {
    "judul": "OPTIMIZING DISTRIBUTED SENSOR NETWORK LIFETIME USING REINFORCEMENT LEARNING ROUTING ALGORITHMS",
    "nama_mahasiswa": "Alex Mercer",
    "nim": "STD-2026-94821",
    "program_studi": "Department of Computer Science & Informatics",
    "departemen": "School of Computing",
    "fakultas": "Faculty of Engineering and Technology",
    "universitas": "Metropolis Institute of Technology",
    "kota": "Metropolis",
    "tahun": "2026"
  },
  "bab1_data": {
    "latar_belakang": [
      "The rapid proliferation of Internet of Things (IoT) devices in environmental monitoring has introduced critical challenges regarding power efficiency and network longevity in wireless sensor networks (WSNs).",
      "Conventional routing protocols, such as static shortest-path routing, frequently exhaust intermediate relay nodes prematurely, resulting in network fragmentation and degraded data reliability.",
      "To overcome these operational constraints, this research proposes an adaptive reinforcement learning routing mechanism that dynamically balances energy expenditure across network nodes while sustaining throughput."
    ],
    "rumusan_masalah_pengantar": "Based on the operational challenges and efficiency gaps identified above, the primary research question is formulated as follows:",
    "rumusan_masalah": "To what extent does the proposed reinforcement learning routing algorithm improve overall network lifetime and packet delivery ratio compared to conventional static routing protocols in large-scale wireless sensor networks?",
    "rumusan_masalah_penjelasan": "This single research question evaluates the causal relationship between the independent variable (reinforcement learning routing mechanism) and key dependent performance indicators (network operational lifetime and packet delivery ratio).",
    "tujuan_umum": "evaluate and quantify the network longevity and transmission efficiency improvements achieved by the reinforcement learning routing protocol compared to baseline routing approaches.",
    "tujuan_khusus": [
      "Analyze the energy consumption profiles and bottleneck factors in baseline sensor routing workflows.",
      "Design and model the adaptive reinforcement learning routing algorithm.",
      "Develop a proof-of-concept simulation environment for multi-hop sensor networks.",
      "Evaluate network lifetime, packet delivery ratio, and convergence time through rigorous benchmark simulations."
    ],
    "manfaat": [
      "For Sensor Network Practitioners: Provides an operational blueprint for resilient and energy-balanced wireless sensor deployments.",
      "For Academic Researchers: Contributes empirical evidence and benchmark datasets regarding reinforcement learning applications in low-power communication systems."
    ],
    "batasan_masalah": [
      "Evaluation is conducted within a simulated network environment consisting of 100 to 500 heterogeneous nodes.",
      "Hardware-level physical layer modifications are outside the scope of this investigation.",
      "Channel conditions are modeled based on standard log-distance path loss propagation."
    ],
    "sistematika_pembahasan": [
      "CHAPTER 1 INTRODUCTION: Details background context, research problem formulation, objectives, practical and theoretical benefits, scope limitations, and outline.",
      "CHAPTER 2 LITERATURE REVIEW: Synthesizes foundational networking concepts, reinforcement learning formulations, prior benchmark studies, and identified research gaps.",
      "CHAPTER 3 METHODOLOGY: Defines research design, experimental testbed parameters, evaluation metrics, and timeline."
    ]
  },
  "bab2_subbab": [
    {
      "title": "Wireless Sensor Network Routing Protocols",
      "level": 2,
      "paragraphs": [
        "Routing protocols in sensor networks must strike a delicate balance between routing overhead and battery conservation. Standard multi-hop schemes often incur uneven drain rates on central clusters."
      ]
    },
    {
      "title": "Reinforcement Learning in Dynamic Networks",
      "level": 2,
      "paragraphs": [
        "Q-learning and policy-gradient algorithms enable decentralized agents to discover optimal forwarding policies through continuous environmental reward feedback."
      ]
    }
  ],
  "bab3_subbab": [
    {
      "title": "Simulation Design and Experimental Setup",
      "level": 2,
      "paragraphs": [
        "The experimental framework is implemented using an event-driven network simulator modeling randomized node deployments and Poisson packet arrival processes."
      ]
    }
  ],
  "daftar_referensi": [
    "Akyildiz, I.F., Su, W., Sankarasubramaniam, Y. & Cayirci, E., 2002. Wireless sensor networks: a survey. Computer Networks, 38(4), pp.393–422.",
    "Sutton, R.S. & Barto, A.G., 2018. Reinforcement learning: An introduction. 2nd ed. Cambridge: MIT Press."
  ],
  "output_filename": "Proposal Skripsi v1.0.docx"
}

{
  "topic": "Optimizing Distributed Sensor Network Lifetime using Reinforcement Learning Routing Algorithms",
  "variabel_x": "Reinforcement Learning Adaptive Q-Routing",
  "variabel_y": "Network Operational Longevity and Packet Delivery Ratio",
  "csv_filename": "literature.csv",
  "output_filename": "Proposal Skripsi v1.0.docx"
}

{
  "topic": "Optimasi Deteksi Anomali Jaringan IoT Menggunakan Federated Learning",
  "variabel_x": "Algoritma Federated Learning Terdistribusi",
  "variabel_y": "Akurasi Deteksi dan Efisiensi Komunikasi Jaringan IoT",
  "student_metadata": {
    "nama_mahasiswa": "Alex Mercer",
    "nim": "225150200111000",
    "jurusan": "Teknik Informatika",
    "program_studi": "Teknik Informatika",
    "keminatan": "Komputasi Cerdas",
    "bidang_skripsi": "Artificial Intelligence & Data Science",
    "jenis_penelitian": "Implementatif",
    "tipe_penelitian": "Pengembangan Sistem & Komparasi Algoritma",
    "asal_judul": "Usulan Sendiri",
    "lokasi": "Malang",
    "nama_pembimbing": "Dr. Mahrus Ali, S.Kom., M.Kom.",
    "nip_pembimbing": "-"
  },
  "output_filename": "Praproposal_Skripsi_SA2-01A.odt"
}

Author,Year,Title,Method,Dataset,Findings,Gap
Zhang et al.,2023,Q-Learning for WSN Clustering,Q-Learning,WSN-Sim-100,Increased lifetime by 18%,High computational overhead on edge nodes
Al-Kandari et al.,2022,Energy-aware Routing Protocols,Heuristic Path Selection,Real-world Sensor Grid,Reliable packet delivery,Static pathing causes early node death