Couchloop EQ
About
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
Details
- Author
- wisenbergg
- Downloads
- 236
- Categories
- Other, Developer Tools, Security
Jump to
- Behavioral governance with hallucination detection and consistency checking
- Stateful session management preserving context across interactions
- Privacy‑by‑design: no personal data stored, session‑based isolation
- Ten primary MCP tools: couchloop, guard, verify, status, conversation, brainstorm, code_review, package_audit, remember, protect
- Safety guardrails against harmful advice, clinical overreach, and manipulation
- OpenTelemetry distributed tracing across all stages
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Couchloop EQCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Couchloop EQ works with any MCP‑compatible client (Claude Desktop, ChatGPT, Cursor, Windsurf, VS Code, etc.). The easiest way is to connect to the hosted production endpoint at https://mcp.couchloop.com/mcp using streamable-http transport. For local use, install the npm package couchloop-eq-mcp globally and add the server configuration to your client’s MCP settings. No signup or API key is required; sessions persist automatically to ~/.couchloop-mcp/identity.json.
create_session
Start a new guided session. Optionally specify a journey to follow.
send_message
Send a message through the therapeutic AI stack with crisis detection and emotional support.
resume_session
Resume a previously paused session. Returns current state and next step.
save_checkpoint
Save progress or capture a key moment in the current session.
get_checkpoints
Get all checkpoints for a session.
list_journeys
List available guided journeys/experiences.
get_journey_status
Get current progress in a session/journey.
save_insight
Capture a meaningful insight or realization from the conversation.
get_insights
Get user insights, optionally filtered by session.
get_user_context
Get relevant context about this user for personalization.
validate_packages
Validate package dependencies to prevent installation of non-existent or malicious packages
pre_review_code
Pre-screen AI-generated code to catch obvious issues and reduce human review burden. Detects console logs, commented code, TODOs, missing error handling, hardcoded values, type issues, and code complexity problems.
scan_security
Comprehensive security scanner for AI-generated code. Detects SQL injection, XSS, hardcoded secrets, and other vulnerabilities with CWE codes and secure alternatives.
detect_code_smell
Detect code bloat, verbose patterns, and over-engineered code that creates technical debt. Analyzes complexity metrics and suggests simplifications.
protect_files
Prevents accidental file deletion and destructive operations. Validates operations against protected paths and patterns, creates automatic backups, and provides rollback capability.
get_protection_status
Get current file protection status, configuration, and backup statistics.
get_operation_history
Get history of file operations that were attempted or executed.
list_backups
List all available backup snapshots that can be restored.
rollback_file
Restore a file from a backup snapshot (undo a file modification/deletion).
enable_code_freeze
Enable code freeze mode - all file operations require explicit approval (critical protection mode).
disable_code_freeze
Disable code freeze mode - resume normal file operation protection rules.
preserve_context
Store, retrieve, and manage important project context to prevent AI amnesia when context windows fill up. Preserves architectural decisions, requirements, constraints, and technical patterns across conversations.
check_versions
Validate library versions against latest releases, detect deprecated APIs, and prevent AI from using outdated patterns. Checks for breaking changes, security vulnerabilities, and provides upgrade paths.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"couchloop eq": {
"couchloop-eq": {
"url": "https://mcp.couchloop.com/mcp",
"transport": "streamable-http"
}
}
}
}
McpServers
{
"couchloop-eq": {
"url": "https://mcp.couchloop.com/mcp",
"transport": "streamable-http"
}
}
CouchLoop EQ - MCP Server
Behavioral governance layer for safer, more consistent AI conversations. <p align="center">📖 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 a behavioral governance layer for AI assistants. Built on MCP (Model Context Protocol), it monitors for hallucination, inconsistency, and unsafe reasoning patterns while managing stateful AI sessions.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 |
Architecture
CouchLoop EQ uses a modular pipeline: ``
Request -> Classify -> Policy -> Plan -> Execute -> Compose
`
- Intent Classifier: Confidence-based routing with multi-intent detection
- Policy Engine: Health-aware routing with fallbacks and crisis override
- Execution Planner: DAG generation for parallel operations
- Tool Registry: Health tracking and circuit breakers
- OpenTelemetry: Distributed tracing across all stages
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:
`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
`bash
npm install -g couchloop-eq-mcp
`
Add to Claude Desktop configuration:
`json
{
"mcpServers": {
"couchloop-eq": {
"command": "couchloop-eq-mcp",
"env": {
"COUCHLOOP_SERVER": "https://mcp.couchloop.com"
}
}
}
}
`
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:
1. Enable Developer Mode in ChatGPT Settings
2. Add as MCP connector with URL: https://mcp.couchloop.com/mcp
3. 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 provides 10 MCP tools with intelligent routing. The couchloop intent router handles ambiguous or multi-intent requests, while high-confidence intents can call tools directly.
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. |
Governance
| Tool | Description |
| ------- | -------------------------------------------------------------------------------------------------------- |
| guard | Per-turn governance - Evaluates draft responses before delivery. Actions: pass, modified, or blocked |
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
``Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





