- Myrmex Hive @olafkfreund/myrmex-hiveZero-inbound-port MCP gateway for managing distributed edge servers over reverse SSH tunnels8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- Cogmem @writerslogic/cogmemA self-improving, verifiable memory layer for AI coding agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- TAR Engine @qingxuantang/tar-engineAudit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- MySQL (security-first) @kurok1/mcp-server-mysqlSecurity-first MySQL MCP server with AST validation, table whitelist, schema resources, and audit.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- SupraWall @wiserautomation/suprawall-mcpSupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- VeriSwarm @veriswarm/veriswarm-mcpVeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Agentrisk @trycoin-ai/agentriskRisk guardrails for AI trading agents. Your agent proposes; your policy decides.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Zyrax Guard @tiagosilva07/zyrax-guardAudit AI agent configs for prompt injection & rogue MCP servers; vet packages6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Promptrejectormcp @revsmoke/promptrejectormcpSecurity gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Presidio Hardened X402 @presidio-v/presidio-hardened-x402-mcpPre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Shinobi @numbererikson/shinobiTask spine + searched dead ends + approvals for AI coding agents. One brain, every device.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Qorami @loicfontaine-max/qoramiCheck an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Figuard @figuard/figuard-mcpPre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Waxseal @degenlegion-com/waxsealEd25519 identity for AI agents. Verify seals, sign documents, gate actions with approvals.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Frugal @brainsparker/frugalThe open routing layer for AI tools: tool calls routed per policy, decision on every result.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- OmniGlyph @aidi1723/omniglyphLocal symbol ground truth MCP server for Unicode lookup and code-symbol linting.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Shrike @shrike-security/shrike-mcpGoverns what AI agents do: tool calls, SQL, commands, files checked against policy before they run.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Agent Trust @garl-protocol/agent-trustTamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Yieldagentx402 @fabio662/yieldagentx402Policy-gated x402 MCP for agent workflows with TEE receipts, 18 tools, and no custody.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Kasbah @al-adnane/kasbah-mcpGovernance layer for agentic AI — signed, verifiable receipts for every agent action.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- XAPS MCP Server @apmc1/xapsPre-execution audit for autonomous agents. Independent receipt before irreversible actions.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- 1Claw Vault @1clawai/1claw-mcpHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- ljos @leidarljos/ljosLocal memory, a work tracker and a shell-command guard shared by coding agents on one machine.Not assessed yet.Runs on your machine, installed from cargo.1 GitHub stars.
- LogCarverGuard @caiderek/logcarverguardGuardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.1 GitHub stars.
