mcp-server-decisions
About
Decision tracking with prediction validation and outcome gates for AI agents
Details
- Author
- roberton003
- Categories
- Developer Tools
Jump to
Setup
Install mcp-server-decisions in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/roberton003/mcp-server-decisions
Follow the installation instructions in the repository README, then restart your MCP client.
Servidor MCP para governança e rastreamento de decisões arquiteturais.
⚡Zero External Dependencies• Stdlib-only Python • Append-only JSONL storage • Fully portable
- 🎯 Decision Recording— Capture architectural choices with problem statement, solution, rejected alternatives, and target technologies.
- 📈 Prediction Linking— Attach testable claims (latency, cost, scalability, reliability) tied to decisions.
- ✅ Outcome Validation— Record measured results and automatically compute accuracy scores (0–100 scale).
- 📊 Technology Performance Registry— Aggregate success rates and confidence metrics per technology over time.
- 🚪 Outcome Gate Pattern— In-band nudges inside tool responses prevent decision feedback loops from leaking (3.8% → 14.5%closure rate).
- ⚡ Zero Dependencies— Portable append-only JSONL log. No database servers, no migrations, no background daemons.
# Agent or user records a choice: record-decision( problem="Query latency exceeds SLA (p99 > 500ms)", chosen_solution="DuckDB + Parquet caching", rejected_alternatives=["Redis", "Elasticsearch"], technologies=["duckdb", "parquet"], predictions=[ {"prediction_type": "LATENCY", "predicted_value": "p99 < 200ms"}, {"prediction_type": "COST", "predicted_value": "< $50/month"} ] ) # ➔ Returns: DEC-2026-0001, PRD-2026-0001, PRD-2026-0002
record-outcome( prediction_id="PRD-2026-0001", actual_value="p99 = 180ms", measurement_source="MONITORING", accuracy_score=95 ) # ➔ Returns: SUCCESS ✅ (95% accuracy)
3️⃣ Query Prior Decisions & Technology Stats
# Search past decisions before choosing a technology: query-decisions(technology="duckdb", max_results=5) # View aggregated technology performance: python3 scripts/technology_performance_report.py # ➔ Output: # technology: duckdb | successful: 12 | failed: 1 | avg_accuracy: 91.2% | confidence: HIGH
# From PyPI (once published) or local editable install: pip install -e .
Add to your MCP client configuration (e.g. Claude Desktop, Claude Code, Cursor, OpenCode):
{ "mcpServers": { "mcp-server-decisions": { "type": "stdio", "command": "mcp-server-decisions" } } }
For client-specific setup guides (Claude, OpenCode, Codex, Antigravity), see 📖docs/INTEGRATIONS.md.
Decide → Predict → Implement → Measure → Validate → Learn → Next Decision
- Record a decision— Store the problem, chosen solution, alternatives, and technologies
- Make predictions— Attach testable claims (latency, cost, reliability, etc.)
- Implement— Build the system
- Measure results— Capture actual values from monitoring, logs, benchmarks
- Validate— The server calculates accuracy (0-100) and validation status (SUCCESS / PARTIAL_SUCCESS / FAILED)
- Learn— Review what worked via the Technology Performance Registry
- Next decision— Query past decisions before making new recommendations
Decision loops leak because predictions aren't validated. This server embeds a reminder directly in tool responses:
- Decision is made → implementation starts → results come in → nobody checks if prediction was right
{ "decision_id": "DEC-2026-0001", "status": "OK", "OUTCOME_GATE": "⚠️ 2 prediction(s) from this session still lack outcomes: [PRD-2026-0001, PRD-2026-0002]. Record results via record-outcome before ending." }
The nudge is in-band (inside the tool response), where agents are already looking. Result:3.8% → 14.5% closure rateimprovement (validated on internal tool).
Real Example: After recording a decision with 3 predictions, the response includes:
{ "decision_id": "DEC-2026-0042", "prediction_ids": ["PRD-2026-0051", "PRD-2026-0052", "PRD-2026-0053"], "status": "OK", "OUTCOME_GATE": "⚠️ 3 prediction(s) from this session still lack outcomes: [PRD-2026-0051, PRD-2026-0052, PRD-2026-0053]. Record results via record-outcome before ending." }
Next query still shows the gate until all 3 outcomes are recorded. Once they are, the gate disappears automatically.
For the full pattern explanation, seedocs/OUTCOME-GATE-PATTERN.md.
- Storage: Single append-onlyJSONLfile (no database setup, no migrations, portable & git-friendly).
- IDs: Sequential per calendar year (DEC-2026-0001,PRD-2026-0002,OUT-2026-0003).
- Accuracy Scoring: Automatic classification (≥90SUCCESS,50–89PARTIAL_SUCCESS,<50FAILED).
- Runtime: Stdlib-only Python 3.10+ (zero external pip runtime dependencies).
- Protocol: Model Context Protocol (JSON-RPC 2.0 over stdio).
python3 server.py --selftest # ➔ ✅ All self-tests passed
See 📝CONTRIBUTING.mdto contribute features or fixes.
- Core decision / prediction / outcome tracking
- Outcome Gate in-band nudges
- Technology Performance Registry
- Web UI for browsing & searching decisions
- Webhooks / notifications on low prediction accuracy
- Pre-built decision templates & domain patterns
This project is community-built and independent. It is not affiliated with any organization or standard-setting body.
Servidor MCP para governança e rastreamento de decisões arquiteturais.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Create crafted UI components inspired by the best 21st.dev design engineers.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
ALAPI MCP Tools,Call hundreds of API interfaces via MCP
AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.
One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
