- opchain @asfbay-bit/opchain-skillsClaude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- DevOps Practices @ai-4-devops/devops-practicesProductivity framework for DevOps engineers using AI assistance (Claude Code) while working on PoCs4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- vaultit @therealdataboss/vaultitZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.24% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- N3MemoryCore Lite (Working Memory) @neuralnexusnote/n3mc-workingmemoryEphemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Lethe @jesusgarcia9009/letheContext GC for LLM agents: offload large tool outputs and recall them to save tokens.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Sports Context Protocol @dswane/sports-context-protocolSelf-learning operational context layer for AI sports agents. Profile 001: golf.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Creedspace @creed-space/creedspace-mcp-serverConstitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Threadmap @advertflair/threadmap-mcpConversation drift visualization for Claude. Color-coded inflection points and one-click forking.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Sutra @4rgon4ut/sutraContext Engineering Engine. Provides cognitive tools, memory structures, and agent patterns.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Gildara MCP @gildara/mcp-serverOperating contracts for AI agents. Structured instructions compiled into system prompts.16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- DeerDawn Remote MCP @deerdawn/deerdawnAI session memory: the brief your AI reads before every session so no session starts cold.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Skill Builder @dmzagent/skill-builder-mcpSearch the skill-builder registry and auto-install skills for Claude Code, Cursor, and Codex.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Savanto MCP @savantoai/mcp-serverManage your Savanto store from your AI: catalog, content, prompts, and analytics, by chat.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Assay Truth Graph MCP @assay-org/assay-truth-graphGround GTM agents in governed, cited company truth.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Brivvy MCP @brivvyhq/mcpBrivvy MCP (OAuth): on-brand AI content, voice rules, templates, glossary.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- HuangtingFlux — Huangting Protocol MCP Server @xiandao-labs/huangting-fluxReduces AI Agent token usage by 40% via three-stage SOP workflow.25% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Rtkcontext @clauxel/rtkcontext-mcpA paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- AgentTune — personality tunings for AI agents @agent-tune/agenttunePersonality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Marcora @marketcore/mcpTools for creating on-brand marketing content using Marcora's intelligent context infrastructure.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- jitprompt @jitprompt/jitpromptJust-in-time instructions for agents: upload docs, serve only the sections each turn needs.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Investboard @investboard/investboardInvestment rules and decision history for AI assistants: read your policy, check changes, review.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Harbor (gethrbr) @gethrbr/harborTeam memory for coding agents: rules you approve, served to every agent, and which ones it cited.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- a4sx sessions @session-exchange/sessionsSearch coding-agent sessions and load one as starting context; save your own to your library.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Atendio @atendio/mcpRead WhatsApp conversations and analytics, and manage AI assistant rules in Atendio.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
