- SYNAPSE CHANNEL @anulum/synapse-channelLocal-first multi-agent coordination for messages, leases, shared plans, status, and resources.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Arkgate @pedroknigge/arkgateWhen the agent writes a bad import, the write doesn’t land. The same check fails the pull request.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Kakunin @kakunin-ai/kakuninX.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Runeward @runewardd/runewardGoverned execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- AISentinel by BizDNAi @kabzhanov/aisentinelPre-tool policy enforcement + JSONL audit for AI agents. Apache 2.0.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- ARGUS-3 MCP Server @alexar76/argus3ARGUS-3 stdio MCP with WARDEN firewall: argus_ask, argus_status, argus_capabilities.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- mcp-armor @studiomeyer/armorSecurity sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.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.
- OpenClaw Control @smurfy92/openclaw-control-mcpMCP server bridging Claude Code to the OpenClaw gateway management plane via JSON-RPC.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Stratum MCP @smartmemory/stratum-mcpStructured execution for coding agents: contracts, postconditions, gates, guardrails.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Slang Workflows @shofer-dev/slang-workflowsProvable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- mcp-lint @robert19001-cmyk/mcp-lintLint MCP tool schemas for cross-client compatibility and agent preflight safety.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Holomime @productstein/holomimeBehavioral therapy for AI agents — self-diagnosis, alignment, and training via MCP7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Ark @pedroknigge/arkArchitecture co-pilot for AI TypeScript (write gate, CI, plan/loop)Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- Launcher @oneprofile-dev/mcp-launcherSingle MCP hub: discover, add, audit, and govern MCP servers across every AI client.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- PQC-Khepra MCP — CMMC Autopilot & AI Security Recorder @nouchix/pqc-khepra-mcpPost-quantum CMMC compliance scanner & AI agent attestation. FIPS 140-3, ML-DSA-65, 36K+ mappings.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Paybond MCP Server @nonameuserd/paybondDefault trust layer for agentic payments: authorize agent spend, evidence, receipts, settlement.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Agent Firewall @mlawsonking/agent-firewall-mcpInput/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Cordon for MCP @marras0914/cordonCordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Kubeleash @kubeleash/kubeleashKubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- 402sentinel @kaditang/402sentinel-mcpx402 payment safety for AI agents: counterparty risk gate, payment firewall, compliance, RWA gate.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Securecode @juanisidoro/securecodeSecrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Entropy0dev MCP @entropy0dev/mcpEntropy0 MCP server — source trust and URL safety tools for AI agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Dingdawg Code Review @dingdawg/dingdawg-code-reviewAI code review — security, quality, performance. Learns your patterns. Receipted.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
