trackmcp
Back to directory
Roberton003

mcp-server-decisions

View on GitHub

Servidor MCP para rastreamento de decisões arquiteturais com validação de predições e outcome gates.

0 stars PythonOthers Updated Sep 3, 2026
ai-agentsarchitecturedecision-makingmcpvalidationpython

Documentation

🧠 MCP Server: Decisions

An open-source MCP server that helps teams record architectural decisions, connect them to testable predictions, and validate outcomes over time. It gives AI agents and developers a lightweight, auditable memory for technical choices.

Python 3.10+
MCP
License: MIT
PyPI
Glama
Architectural Decision Feedback Loop with Outcome Gates

✨ Project Highlights

  • Outcome-linked decisions — connect each technical choice to measurable predictions and observed results.
  • In-band outcome gates — tool responses identify predictions that still need validation before the work is considered complete.
  • Portable storage — append-only JSONL keeps the log inspectable, easy to back up, and free from database setup.
  • Zero runtime dependencies — Python's standard library is enough to run the server.
  • MCP-native interface — expose decision tracking through JSON-RPC over stdio to MCP-compatible clients.
  • Technology feedback — aggregate validated outcomes to inform future technology choices.

🧰 Technical Stack

LayerTechnology
ProtocolModel Context Protocol over JSON-RPC 2.0
RuntimePython 3.10+
StorageAppend-only JSONL file
PackagingPyPI / Hatchling
TestingBuilt-in self-test command
LicenseMIT

🔄 Architecture

mermaid
flowchart TD
    A[MCP client or AI agent] --> B[JSON-RPC over stdio]
    B --> C[mcp-server-decisions]
    C --> D[Record decision]
    C --> E[Attach prediction]
    C --> F[Record outcome]
    C --> G[Query decisions and technology history]
    D --> H[(Append-only JSONL log)]
    E --> H
    F --> H
    G --> H
    F --> I[Validation status and accuracy]
    I --> J[Future technical decisions]

📌 What It Provides

The server exposes four tools:

ToolPurpose
`record-decision`Store the problem, chosen solution, alternatives, technologies, and predictions.
`record-prediction`Add a measurable prediction to an existing decision.
`record-outcome`Record the observed result and classify the prediction as success, partial success, or failure.
`query-decisions`Search decisions by keyword, technology, domain, or result limit.

Example flow

text
Decide → Predict → Implement → Measure → Validate → Learn

A decision can produce an outcome-gate reminder such as:

json
{
  "decision_id": "DEC-2026-0001",
  "status": "OK",
  "OUTCOME_GATE": "2 prediction(s) still lack outcomes."
}

The reminder is a workflow signal, not a claim about adoption or measured impact. See the Outcome Gate Pattern for the design and trade-offs.

📊 Current Project Status

AreaStatus
Decision, prediction, and outcome trackingAvailable
Outcome-gate remindersAvailable
Technology performance reportAvailable
PyPI packagePublished as `1.0.2`
External adoption metricsNot collected yet
Web UI and notificationsRoadmap

The project is early-stage. Contributions, examples from real projects, and feedback are welcome.

🚀 Setup

Prerequisites

  • Python 3.10 or newer
  • An MCP-compatible client

Install from PyPI

bash
python3 -m pip install mcp-server-decisions

Run the self-test

bash
python3 -m pip install -e .
python3 server.py --selftest

Configure an MCP client

json
{
  "mcpServers": {
    "mcp-server-decisions": {
      "command": "mcp-server-decisions"
    }
  }
}

For client-specific configuration and troubleshooting, see Client Integrations. For a guided first run, see Quick Start.

Configure the log path

By default, the server writes to `~/.local/share/mcp-decisions/decisions_log.json`. Set `MCP_DECISIONS_LOG_PATH` to use another file:

bash
MCP_DECISIONS_LOG_PATH=/path/to/decisions.json mcp-server-decisions

🗂️ Project Structure

text
.
├── server.py                         # MCP server and tool implementations
├── scripts/                          # Reports derived from the decision log
├── docs/                             # Architecture, examples, and integrations
├── .github/ISSUE_TEMPLATE/           # Reusable bug and feature templates
├── CONTRIBUTING.md                   # Development and contribution workflow
├── QUICKSTART.md                     # Guided setup and first decision
├── server.json                       # MCP Registry metadata
├── pyproject.toml                    # PyPI package metadata
└── LICENSE                           # MIT license

📚 Documentation

🛣️ Roadmap

  • [x] Core decision, prediction, and outcome tracking
  • [x] Outcome-gate reminders
  • [x] Technology performance reporting
  • [ ] Web UI for browsing and searching decisions
  • [ ] Notifications for low prediction accuracy
  • [ ] Reusable decision templates and domain patterns

🤝 Contributing

Issues and pull requests are welcome. Start with CONTRIBUTING.md, run the self-test, and explain the problem or use case in the pull request.

📄 License

MIT © 2026 Roberto Nascimento

Frequently asked questions

What is mcp-server-decisions?

mcp-server-decisions is Servidor MCP para rastreamento de decisões arquiteturais com validação de predições e outcome gates.

How do I install mcp-server-decisions?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is mcp-server-decisions open source?

Yes — it is hosted on GitHub at https://github.com/Roberton003/mcp-server-decisions.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP