Install
$ agentstack add mcp-thedecipherist-rulecatch-sdk ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Rulecatch SDK
Official open-source packages for Rulecatch — AI coding analytics, monitoring, and rule enforcement for Claude Code.
Track every AI coding session in real-time: tool calls, file edits, token usage, costs, and rule violations. Privacy-first with zero-knowledge encryption.
Packages
| Package | Description | npm | |---------|-------------|-----| | [@rulecatch/ai-pooler](./packages/ai-pooler) | CLI + hooks for tracking AI coding activity | [](https://www.npmjs.com/package/@rulecatch/ai-pooler) | | [@rulecatch/mcp-server](./packages/mcp-server) | MCP server — query violations and rules from Claude Code | [](https://www.npmjs.com/package/@rulecatch/mcp-server) |
Quick Start
Monitor AI activity (no account needed)
npx @rulecatch/ai-pooler monitor --no-api-key
See what your AI coding assistant is doing in real-time — tool calls, file edits, tokens, costs. Zero setup.
Full setup (with dashboard)
# 1. Install and configure
npx @rulecatch/ai-pooler init
# 2. Start the live monitor
npx @rulecatch/ai-pooler monitor
# 3. (Optional) Add MCP server for in-IDE rule violations
# Add to ~/.claude/mcp.json:
# { "mcpServers": { "rulecatch": { "command": "npx", "args": ["-y", "@rulecatch/mcp-server"] } } }
What It Tracks
- Tool calls — every Read, Write, Edit, Bash, Grep, Glob with success/failure and I/O size
- Token usage — input/output tokens per model, running totals
- Cost — real-time cost estimation by model (Opus, Sonnet, Haiku)
- Code changes — lines added/removed via git diff
- Session timeline — start, end, duration, active time
- Rule violations — custom rules enforced across your team
Privacy
All personal data (file paths, emails, project names) is encrypted on your machine before it leaves. We use AES-256-GCM with PBKDF2 key derivation (100k iterations). Your encryption key never leaves your device.
Read more about our privacy architecture
How It Works
Claude Code hooks → local buffer → flush to API → dashboard
↓
rule engine → violation alerts
- Hooks capture events from Claude Code (zero token overhead — hooks run in bash)
- Buffer stores events locally as JSON files
- Flush sends batched events to the Rulecatch API (encrypted)
- Dashboard shows analytics, trends, and team insights
- Rules are checked in real-time and violations surface in the MCP server
Links
License
MIT
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: TheDecipherist
- Source: TheDecipherist/rulecatch-sdk
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.