- Cogmemai @hifriendbot/cogmemaiMemory for any Ai: remembers across sessions, enforces your rules before actions, reviews the work.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- SafeAgent @azender1/safeagentExactly-once execution guard for AI agents. Prevents duplicate payments and webhooks on retry.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- Marrow AI: Control Layer for AI Agents @getmarrow-ai/marrowA named yes before your AI agent acts, plus proof the next agent can reuse. Works in any MCP client.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- PreClick — An MCP-native URL preflight scanning service for autonomous agents (formerly URLCheck). @urlcheck/urlcheck-mcpPreClick scans links for threats and confirms intent match with high accuracy before agents click.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- Assurance @i-ops-hq/assurance-mcpChecks what an agent did NOT read. Coverage over a retrieval step or a folder.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Onchain Agent Wallets @nirholas/onchain-agent-walletsGive an AI agent a Solana spending allowance instead of your key. Chain-enforced cap, x402.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Axis @useaxis/axisCoding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.6 GitHub stars.
- Quilt @wkoverfield/quiltTrack which AI agent wrote which lines in a shared Git checkout; each commits only its own lines.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Telleroutlook MCP @telleroutlook/mcp-serverWasmAgent MCP server — WASM-sandboxed code execution with capability manifests and Tasks API.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Tuning Engines - Governed AI Runtime @cerebrixos-org/tuning-enginesGovern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Hermes Action Bridge @thebluehouse75/hermes-action-bridgeDelegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Trust Oracle @new1direction/trust-oracleIndependent A-F trust grade for any MCP server, watched for drift. Free, never for sale.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- MCP Gateway @panossalt/mcp-gatewayMulti-tenant MCP platform with OAuth 2.1, Entra SSO, RBAC and audit logging.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- ToolMesh @dunkelcloud/toolmeshSelf-hosted MCP gateway. Turn any REST API into MCP tools via YAML (DADL). Authz, audit, policies.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.6 GitHub stars.
- PreClick — An MCP-native URL preflight scanning service for autonomous agents. @preclick/preclick-mcpPreClick scans links for threats and confirms intent match with high accuracy before agents click.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- Poordjaevin @icaro0310/poordjaevinTyped answers with calibrated confidence for agents. Local-first, no API key.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- cmdxray @aurelio-nakamura/cmdxrayOffline MCP server: explains shell commands token-by-token and flags destructive ones for AI agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Kepil @oleg-vdv/kepilPassport, mandate, fail-closed action gate and tamper-evident journal for AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Fagan @motock/faganAutonomous coding pipeline: frontier models plan and review, a local model implements, gated by TDD.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.5 GitHub stars.
- Agent Wormhole @runningoffcode/wormhole-x402Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Pkgdiet @om-tajne/pkgdietPut your node_modules on a diet - find unused dependencies, analyze health, and reduce size4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Warmplane @warmplane/warmplaneLocal MCP control plane for persistent sessions and compact capability discovery.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.5 GitHub stars.
- Norma by Quality Clouds @qualityclouds/normaChecks AI-written code against your rules as it is written, and keeps a record of what it found.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.5 GitHub stars.
- Midplane @midplane/midplaneSafe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
