- agent-exporter MCP bridge @xiaojiou176-open/agent-exporter-mcpLocal stdio MCP bridge for archive publishing, retrieval, and governance evidence.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Rokha @rokha/rokhaSearch a registry of agent skills and MCP servers, then run them for real. No install, traced.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Sutra @shivnathtathe/sutraPrivate, portable memory and reusable skills for AI agents.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- GodPrompt MCP Server @akzar1el/god-prompt-mcpGodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- distil @munhq/distilContext optimization for LLM agents: tool registry, result masking, budgeting, compaction.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Contexter @maaakso/contexterShare one project context across ChatGPT, Claude, Telegram and any MCP client.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Wondel Skills @mjaskolski/wondel-skills-mcpRead-only MCP server over 50 book-based agent skills: routes a task to the right framework.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Monet @team-monet/monetLocal-first, state-centric memory for coding agents. MCP server + CLI.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Context — ctxt.io @ctxt/mcpShare text, markdown, code, or HTML as auto-expiring links4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- memgit @memgit/memgitGit for AI memory — version-controlled, searchable context that persists across sessions4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Handover @handover/handoverShared, versioned context that humans and AI agents can publish, review, annotate, and continue.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- USRCP — User Context Protocol @frank-bot07/usrcpEncrypted local ledger of structured user state, shared across every MCP-aware AI tool.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Yagami AI Context Firewall @matthewtracy/yagamiOpen-source AI context firewall for governed model, retrieval, memory, and tool access.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Token Optimizer @omkar9854/token-optimizerReversible context compression for AI agents: cut token usage up to 94%, originals retrievable6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Skillselion @skillselion/skillselion-mcpOn-demand access to thousands of install-ranked Claude Code skills - search and load mid-task.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Kumbuka @kumbuka/kumbuka-serverGoverned, auditable knowledge your team curates for its AI assistants, self-hostable5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Cybersec @xu-c0/cybersec-mcpCybersecurity MCP server: 323 prompts + 7 workflows for red team, blue team, SOC, cloud, OSINT.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Agent Memory @xultrax-web/agent-memory-mcpMarkdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- PrompyAI @samouh-waleed/prompyaiScores your prompts against your real codebase — context-aware prompt intelligence5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Claude Bridge @rahuljava2807/claude-bridge-mcpPipes Claude Code session output into Claude Chat — no more copy-paste between tools7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Prompeteer @prompeteer/prompeteer-mcpContextual prompts and agent skills for 140+ AI platforms.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Agency @npupko/agency-mcp-serverOn-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- ID Protocol @markoblogo/idPortable human-AI context protocol reference tooling.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Factsets MCP Server @joshua-auchincloss/factsetsAn MCP server that provides a local, persistent, self-maintaining knowledge base for AI agents4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
