# CouchLoop EQ

CouchLoop EQ provides behavioral governance for LLMs. It monitors AI responses for hallucination, inconsistency, tone drift, and unsafe reasoning patterns, while also managing stateful sessions and g…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add couchloop/ceq

# Browse available tools
npx -y @smithery/cli@latest tool list couchloop/ceq

# Get full schema for a tool
npx -y @smithery/cli@latest tool get couchloop/ceq memory

# Call a tool
npx -y @smithery/cli@latest tool call couchloop/ceq memory '{}'
```

## Direct MCP Connection

Endpoint: `https://ceq--couchloop.run.tools`

## Tools (4)

- `memory` — Save and retrieve context, insights, checkpoints, and decisions across conversations. Prevents AI amnesia. Use action "…
- `conversation` — Guided self-reflection, burnout check-ins, and wellness conversations with crisis detection. Routes to therapeutic AI b…
- `review` — Unified code review, package audit, pre-delivery verification, and error correction. Modes: "code" for security/quality…
- `status` — System dashboard — session progress, history summaries, context usage, protection status, and preferences. Use for high…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get couchloop/ceq <tool-name>
```

## Resources

- `session://current` — The active session state, if any
- `journey://daily-reflection` — Full journey definition including all steps
- `journey://gratitude-practice` — Full journey definition including all steps
- `journey://weekly-review` — Full journey definition including all steps
- `context://user` — User preferences and recent history

## Prompts (9)

- `daily-reflection` (mood) — Start a guided daily reflection session to process your day
- `code-review` (code, language) — Review code for security issues, code smells, and best practices
- `validate-dependencies` (packages) — Validate package dependencies for hallucinated or vulnerable packages
- `sprint-kickoff` (sprint_name) — Start a new sprint session to capture context and decisions
- `security-audit` (code, language) — Comprehensive security scan of code for vulnerabilities
- `pre-commit-check` (code, language) — Full code quality check before committing - security, smells, and review
- `check-outdated-deps` (packages, registry) — Find outdated or deprecated dependencies in your project
- `save-architecture` (content, category) — Store current architecture decisions and technical patterns for future reference
- `retrieve-context` (search_term, category) — Retrieve stored context - either recent context or search for specific topic