- contextkeeper @therealdataboss/contextkeeperZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.19% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Forgeprint @forgeprint/forgeprintResolve a developer profile to exactly one project blueprint and return its CI-tested setup recipe.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- specpack @the-kipdev/specpackAudit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Heropedia @siliconroshibill/heropediaConsult 324+ expert personas (Buffett, Jobs, Munger, Torvalds, ...) via 4 read-only registry tools.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sticky @1picassoai/stickyPersistent memory and context for your agent, on a board you can see. Capped, so it stays small.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- OCL Context Layer @nantiai/ocl-standardReference MCP server for OCL, an open standard giving AI agents scoped business meaning for Odoo.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Giljo HQ @giljo/hqContext engineering for AI coding agents: product context, project missions, and 360 memory.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Poly-Glot AI Workspace @hmoses/poly-glot-ai-workspaceMultilingual AI workspace: 1,000+ prompts, Compare Mode, 35 languages, BYOM. Free trial.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- skillkit @furkan708/skillkitToolbox for AI agent skills: scaffold, lint, pack, install, and serve SKILL.md skills4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Skill @chrischall/skill-mcpServes a directory of Agent Skills over MCP: list, load, read files, run declared scripts4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- NightMarquee @ant-dev-lab/nightmarqueeCinematic website prompts plus demo footage, tuned for Lovable, Bolt, Cursor, Claude and Codex.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cap Shield @robinlidberg-dot/cap-shieldContext selection and compression for AI agents - recall measured, not claimed.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ParetoStudio @paretostudio/paretostudio-mcpRead, create, and install your ParetoStudio prompts, agents, and skills from any MCP client.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- UseMyContext.ai @usemycontext/usemycontextPersonal context for AI, written by you and never scraped: your profile and files, any MCP client.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- ALTWEB Context Loader @altweb/altweb-contextLoads signed ALTWEB context capsules — refuses unsigned, tampered, or untrusted by default.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Conductor @icohangar-ops/agent-conductorAGENTS.md + skills MCP with CHP R0 gate and adversary decision tools.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Coding Guides @delian/codeguide-mcpCoding guidelines and best-practice guides for 130+ languages, frameworks, and tools.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TeamShared @xhad/teamsharedShared memory for coding agents. Stop re-explaining your codebase every session.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- KnowledgeRail @deviank88/knowledge-railPersistent, evidence-backed project knowledge and task context for coding agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PCD (Portable Context Deck) @portablecontext/pcdYour portable context layer — load it into any AI.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Context @dacode-dev/agent-context-apiAgent-work MCP: free context preflight and page-read previews, paid x402 HTTP upgrades.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgenticWorkspace @rudrendupaul/agenticworkspaceWraps the AgenticWorkspace CLI as a single generic MCP tool for repo workspace scans.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- HYTHE @hythe/hytheHYTHE — coordination bus + shared truth for AI agent fleets — self-hosted MCP server + stdio bridge.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Orcha @westonhancock/orchaSecurely search and manage workspace context files for AI agents and teams.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
