Skip to content
Roberton003 edited this page Jul 22, 2026 · 3 revisions

Welcome to mcp-server-decisions

Architectural decision tracking with prediction validation and outcome gates.

Quick Links

What is This?

A Model Context Protocol (MCP) server that helps agents and teams:

  1. Record technical decisions (problem, solution, alternatives, technologies)
  2. Predict measurable outcomes (latency, cost, scalability, etc.)
  3. Measure results in production
  4. Validate predictions against reality
  5. Learn from accuracy — improve future recommendations

All backed by an append-only JSONL log. No external database, no schema migrations.

Why It Matters

Decision-making systems typically leak the feedback loop:

  • Agent chooses solution → confirms choice → implementation starts
  • Results come in → but nobody asks: "Was the prediction correct?"
  • Next decision starts → learns nothing from the last one

This server closes that loop automatically. It nudges you in-band (inside tool responses) when predictions are pending, keeping closure rates high.

Start Here

Quick Start Guide (5 minutes to your first decision)

Core Concepts

Decision

A choice made at a point in time:

  • Problem being solved
  • Chosen solution
  • Alternatives considered
  • Technologies involved

Prediction

A testable claim linked to a decision:

  • Type (LATENCY, COST, SCALABILITY, RELIABILITY, etc.)
  • Predicted value (e.g., "p99 < 200ms", "cost < $100/month")

Outcome

Measured reality:

  • Actual value observed
  • Measurement source (MONITORING, LOGS, BENCHMARK, etc.)
  • Accuracy score (0-100)

Outcome Gate

In-band nudge embedded in tool responses:

  • Appears automatically if predictions from this session lack outcomes
  • No external reminders needed — nudge is co-located with the decision
  • Dramatically improves closure rates (3.8% → 14.5% observed)

Performance Registry

Automatic aggregation by technology:

technology: duckdb          | successful: 12 | failed: 1 | avg_accuracy: 91.2% | confidence: HIGH
technology: redis           | successful:  8 | failed: 3 | avg_accuracy: 78.3% | confidence: MEDIUM

Use this before recommending a technology — learn from what's actually worked.

Support


Made for AI agents. Built for teams. Learn from every decision.

Clone this wiki locally