Code

Vet third-party AI agent extensions + agent-config files (AGENTS.md, .cursor/rules, CLAUDE.md).

Verify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.

Connect coding agents to your Althea and, through her, a consent-first network of ML researchers.

Human-authenticated setup for routing GitHub pull requests into the right Slack channel.

OAuth-protected Streamable HTTP MCP server. One coach account per token, with tools for the review queue, conversations, leads, and booking.

Look up what your verification method cannot see: 48 failures that report success.

An LLM-based code review MCP server with AST-powered smart context extraction

Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.

Git-native project memory for AI assistants with enterprise-grade audit compliance

Debug and develop MCP servers with hot-swapping, session recording, and playback testing

Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.

Deterministic orchestrator for CLI coding agents. Byte-identical replay, 40+ adapters, air-gap.

Debug AI with shared KB. One bug fixed = everyone benefits. KB hit 4ms free, new analysis $0.05.

Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.

Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).

MCP server that scans your repo's dependencies for security vulnerabilities based on published CVEs.

Transactional refactoring MCP with 11 evidence-backed tools, hash-bound previews, and rollback.

Transactional refactoring extension with 11 evidence-backed tools, previews, and rollback.

OzBridge: run Warp Oz agents from any MCP client — Claude Code, Cursor, Codex, VS Code.

Web-app QA for AI agents: 73 Playwright tools — auth, E2E, a11y/SEO/GEO, Web Vitals + Lighthouse