n8n community node for StudioMeyer Memory — long-term AI memory with knowledge graph, semantic search, entity tracking, and session continuity. 56 tools via MCP (incl. interactive 3D knowledge graph visualization, all on the Free plan). Drop-in memory lay

Persistent local memory for any MCP client. SQLite + FTS5 + sqlite-vec hybrid retrieval, bi-temporal asOf queries, contradiction detection, LLM-free reflection. Multilingual embeddings. Knowledge Graph. No cloud, no API keys.

Cinema-grade video production MCP server — 8 tools for recording, editing, effects, captions, TTS, and smart screenshots. Zero-config, works with any MCP client.

MCP Server for StudioMeyer Agents customers — read your AI-Audit Fleet data and configure your agents from your own Claude/ChatGPT/Cursor.

Linter and security scanner for AI-agent skill and instruction files (Claude Code SKILL.md, AGENTS.md, subagents). Prints an A-F grade, supports --fix, emits JSON + SARIF, ships as a GitHub Action.

AI agents that improve themselves. Self-evolving prompts via A/B testing, multi-model critics, safety gates, and pattern detection.

Multi-agent orchestration framework for Claude Code CLI. Run agents in parallel (Conductor) or stateful workflows with crash-resume + Human-in-the-Loop (Conductor-LangGraph). Subscription-flat by default.

MeetMyAgent as an MCP server — search the free, AI-native marketplace and list your own offers from Claude, Cursor, Codex or ChatGPT. Anonymous discovery works with zero config; an optional API key unlocks listing your business, service or product.

Free 'Memory-First AI Operator' course as an MCP server — take it inside Claude, Cursor, Codex or ChatGPT. Bundled curriculum (6 levels + playbooks + recipes), no account needed. Optional API key unlocks progress, quizzes, certificates.

Local-first personal productivity MCP server for Claude, Cursor, and any MCP client. Email, Calendar, Messaging, Search, Image Generation. BYOK, no cloud, no signup.

Defense-in-depth bundle for MCP stdio servers: drop-in guard for child_process.exec/spawn, AST audit CLI for unsanitized shell calls, and a reference MCP server that exposes both. Closes the Ox-Security 200k-server stdio-RCE class.

Conformance test harness for Model Context Protocol servers. Validates JSON-RPC 2.0, spec-version handshake, transport, OAuth 2.1 PKCE, tool schemas, capabilities, smoke roundtrip, and annotations against MCP spec 2024-11-05 / 2025-03-26 / 2025-06-18 / 20

AI agents that improve themselves. Self-evolving prompts via A/B testing, multi-model critics, safety gates, and pattern detection.

LangGraph.js adapter for darwin-agents — wrap self-evolving Darwin agents as StateGraph nodes with zero hard deps. V0.5.4 opens the darwin-agents peer range to any 0.x (ends the per-minor install breakage; verified against 0.11). V0.5.2 wires the runAgent

CLI tool that scans MCP-server codebases for incompatibilities with MCP-Spec 2026-07-28 RC (Stateless Core, mandatory headers, deprecations, error-code shift, OAuth hardening) and applies safe AST-rewrites where mechanically possible.

AsyncLocalStorage-backed tenant + actor context propagation for MCP servers and request-scoped Node services. Keep tenantSlug and the request actor out of every handler signature. Zero runtime dependencies.

Correct, leak-safe caching for the new MCP cache semantics (SEP-2549). Set ttlMs/cacheScope on the server, and honor them safely on the client/proxy so a private result is never served across authorization contexts.

W3C Trace Context bridge for the Model Context Protocol — propagate traces through MCP _meta and emit OpenTelemetry spans so Host -> MCP server -> tool -> downstream shows up as one trace.

CLI for inspecting and operating mcp-tenant-pair stores

Optional ONNX ML classifier for ai-shield — DeBERTa-style prompt-injection detection alongside heuristic patterns