couchloop-eq-mcp

v1.4.2

Published

a day ago

Behavioral governance layer for LLMs - monitors for hallucination, inconsistency, tone drift, and unsafe reasoning while managing stateful AI sessions

CouchLoop EQ — MCP Server

Behavioral governance layer for safer, more consistent AI conversations.

📖 Choose Your Guide

| Use Case | Guide | Description | | ----------------- | ------------------------------------------ | ------------------------------------------------------------------------ | | 💻 Developers | README-DEVELOPER.md | Package validation, security scanning, code review, context preservation | | 🧘 Wellness | README-WELLNESS.md | Guided sessions, journeys, insights, reflection tools |

What is CouchLoop EQ?

CouchLoop EQ is an MCP (Model Context Protocol) server that provides behavioral governance for LLMs. It monitors AI responses for hallucination, inconsistency, tone drift, and unsafe reasoning patterns—while also managing stateful sessions and guided journeys that remember where you left off.

Why CouchLoop EQ?

Unlike raw LLMs that can hallucinate packages, generate insecure code, and lose context mid-conversation, CouchLoop EQ catches problems before they ship:

| Problem | CouchLoop EQ Solution | | ---------------------------- | ----------------------------------------------------------------------------- | | 🎭 Hallucinated packages | verify + package_audit catch fake npm/PyPI/Maven before install | | 🔓 Insecure code | code_review detects SQLi, XSS, hardcoded secrets | | 📉 Code bloat | code_review flags over-engineering, console.logs, missing error handling | | 🧠 Lost context | remember stores architecture decisions and checkpoints across sessions | | 🗂️ Accidental deletion | protect with automatic backups, freeze mode, and rollback | | 📚 Deprecated APIs | package_audit warns about outdated versions and breaking changes | | 🔍 Sloppy AI code | verify pre-checks AI responses for hallucinated APIs and bad imports | | 💡 Unstructured thinking | brainstorm helps think through trade-offs, compare options, decompose ideas |

Key Safety Features

Behavioral Governance

Hallucination Detection: Monitors for fabricated facts and unsupported claims
Consistency Checking: Identifies contradictions and logical incoherence across turns
Tone Monitoring: Detects emotional escalation, manipulation, or dependency-forming language
Safety Guardrails: Prevents harmful advice, clinical overreach, and inappropriate moralizing

Session Management

Stateful Conversations: Maintains context across multiple interactions
Progress Tracking: Remember where users left off in guided journeys
Crisis Detection: Integrated crisis detection with guided self-reflection journeys
Memory Context: Preserves important insights and checkpoints

Privacy by Design

No personal data stored: No emails, names, passwords, or API keys
Session-based isolation: Each session is anonymous and isolated
Your data stays yours: Insights and context are tied to session IDs, not identities
No tracking: No analytics, no telemetry, no third-party data sharing

Quick Start

CouchLoop EQ is a standard MCP server that works with any MCP-compatible client—Claude Desktop, ChatGPT, Cursor, Windsurf, VS Code, and more.

Option 1: Connect to Hosted Server (Easiest)

Production endpoint: https://mcp.couchloop.com/mcp

For Claude Desktop (v0.7.0+), add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "couchloop-eq": {
      "url": "https://mcp.couchloop.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Restart Claude and try: "Start a daily reflection session"

Option 2: Run Locally (v1.2.0)

npm install -g couchloop-eq-mcp

Add to Claude Desktop configuration:

{
  "mcpServers": {
    "couchloop-eq": {
      "command": "couchloop-eq-mcp",
      "env": {
        "COUCHLOOP_SERVER": "https://mcp.couchloop.com"
      }
    }
  }
}

New in v1.0.4: Sessions automatically persist locally to ~/.couchloop-mcp/identity.json - no signup required!

For ChatGPT (Developer Mode)

ChatGPT supports MCP servers through Developer Mode. See CHATGPT_SETUP.md for detailed setup instructions.

For Other MCP Clients

Any MCP-compatible client (Cursor, Windsurf, Continue, etc.) can connect using:

URL: https://mcp.couchloop.com/mcp
Transport: streamable-http
Auth: None required (session-based isolation)

Production Server Available: https://mcp.couchloop.com/mcp

Quick steps:

Enable Developer Mode in ChatGPT Settings
Add as MCP connector with URL: https://mcp.couchloop.com/mcp
No authentication required - uses session-based isolation

For local development:

Use ngrok or deploy your own server
Follow setup in CHATGPT_SETUP.md

Available Tools (10 Primary)

CouchLoop EQ v1.4.0 uses a 10-tool architecture. The couchloop meta-tool acts as an intelligent router—just say what you want in natural language.

v1.4.0: All tools now execute through a mandatory policy layer (sanitize → verify-if-required → normalize → log), providing consistent output shapes, auto-triggered hallucination checks, and structured audit traces on every call.

Universal Entry Point

| Tool | Description | | ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | | couchloop | Intent router — Routes any loose command to the right tool. Use for: "end session", "save this", "review code", "brainstorm this", "help me", etc. |

Core Tools

| Tool | Description | | --------------- | --------------------------------------------------------------------------------------------------------------------- | | verify | Pre-delivery verification — Catches AI hallucinations, validates packages, checks code before presenting to users | | status | Dashboard — Session progress, history, context window usage, protection status, preferences | | conversation | AI conversation with crisis detection and session memory. Actions: start, send, end, resume, status | | brainstorm | Standalone dev thinking partner — trade-off analysis, feature design, architecture decisions | | code_review | Complete code analysis — security vulnerabilities, code smells, AI-generated errors | | package_audit | Dependency audit — validates packages exist, checks versions, finds vulnerabilities | | remember | Save and recall context, checkpoints, insights across sessions | | protect | File protection — backup, freeze, rollback, restore |

Usage Examples

# Via intent router (recommended for loose commands)
"end session"          → couchloop routes to conversation(action: end)
"save this for later"  → couchloop routes to remember(action: save)
"review my code"       → couchloop routes to code_review
"brainstorm a feature" → couchloop routes to brainstorm
"what can you do"      → couchloop returns capabilities list

# Direct tool calls (for precise control)
conversation(action: "start", message: "Begin daily reflection")
brainstorm(message: "Design a caching layer")  # Dev ideation
remember(action: "recall")  # Get saved context
verify(type: "packages", content: "lodash-utils")  # Validate before install
code_review(code: "function foo()...")  # Analyze code

Real-World Usage

CouchLoop EQ is actively used in production development. Here's what 2 weeks of actual usage looks like:

Usage Statistics

| Metric | Value | | ----------------- | -------------------- | | Insights captured | 49 | | Active sessions | 5 | | Unique tags | 85+ | | Date range | Jan 19 - Feb 2, 2026 |

Development Areas Tracked

| Category | Insights | Example | | ------------------------- | -------- | -------------------------------------------- | | 🔐 Security fixes | 12 | Auth flow hardening, validation improvements | | 💳 Payment integration | 8 | Payment flow patterns, webhook handling | | 📱 Mobile development | 15 | State management, navigation guards | | 🗄️ Database operations | 6 | Data cleanup, schema optimization | | 🏗️ Architecture decisions | 8 | Caching strategies, event patterns |

Featured Insight: Complex Bug Resolution

PAYMENT FLOW BUG ROOT CAUSE IDENTIFIED:

Issue: Race condition between frontend state and backend data caused
inconsistent user experience during payment retry flows.

Analysis: Traced through 5 components across iOS and backend to find
the state synchronization gap.

FIX OPTIONS:
A) Data cleanup - reset stale records
B) Frontend fix - stricter validation
C) Backend fix - additional verification step

Recommended: Defense-in-depth approach combining A + B

This insight was captured mid-debugging session, preserved across context window resets, and referenced 3 days later when implementing the fix.

Best Practices for Sprint Development

Start of sprint: Create a session to establish context

"Create a session for Sprint 42 - user authentication overhaul"

After completing a feature: Save insights, context, or checkpoints depending on complexity

| Feature Size | Recommended Actions | | --------------------- | -------------------------------------------------------------------------------------------- | | Small fix | save_insight — Quick note of what was done and why | | Medium feature | save_insight + save_checkpoint — Capture decisions and state | | Large feature set | preserve_context + save_checkpoint + multiple save_insight — Full architecture context |

Why this matters: When you need to review or debug later, you can retrieve the exact context of what was just built—even weeks later, across different AI sessions.

"Get my insights tagged 'auth-refactor'" → Instant recall of decisions made
"Resume my Sprint 42 session" → Pick up exactly where you left off

Available Journeys

Daily Reflection (5 min) — A brief check-in to process your day
Gratitude Practice (3 min) — Notice and name three things you appreciate
Weekly Review (10 min) — Look back on your week and set intentions

Example Usage

Start a daily reflection:

"Start a daily reflection session"

Resume where you left off:

"Resume my last session"

Save an insight:

"Save this insight: I notice I'm more energized in the mornings"