- sudo-proxy @tarides/sudo-proxyPrivileged command execution proxy with human approval via pkexec or sudo9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.
- agentguard @agentwares/agentguardMCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Guardrail MCP @kadopi/guardrail-mcpDeterministic preflight checks for credentials, fund transfers, writes, and prompt overrides.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MANDATE Credential Broker @projetnanocorp/mandateMCP server for mandates, delegation, policy-gated execution, credential grants, and audit.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Consensus @masterblaster14/consensusCoordination for AI coding agents: declare plans, catch design conflicts early, share team memory.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Working Machines MCP Server @klei30/working-machinesConnect to 1,400+ apps and 15,000+ actions through one OAuth-protected MCP server.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Lauther @csanadymiklos/lautherPuts Approve/Deny on your phone before an agent acts, and waits for your fingerprint.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- WARDEN — MCP Security Firewall @alexar76/wardenMCP security firewall: stdio wrap proxy or inspection tools; zero runtime dependencies.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- GaugeMesh @aliengineering-byte/gaugemeshRoute MCP capabilities through deterministic identity, policy, budget, and deadline constraints.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Raposa Aval — human approval @raposa/raposa-mcpHuman approval for AI agents: a named person approves or rejects, silence is not consent.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Amazon Ads @sellermate/amazon-adsAsk your Amazon Ads account anything and act with guardrails. Remote MCP, OAuth, free to connect.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Living Stack Community @equinoxaifinance-rgb/living-stackFree seven-tool proof loop for scoped authorization, outcome receipts, and evidence-bound claims.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Phosphor @kirusshenkin/phosphorHosts, metrics, Docker and authorized_keys over a macOS terminal's live SSH connections7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- BALMAS @balmasai/balmas-mcpAgents read cleaned copies of your files: PII replaced with local consistent tokens. Read-only.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Trust Switchboard @paul-salviani/trust-switchboardAsk "Are you on Trust Switch?" before your agent deals with another agent. Free. Never blocks.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Delentia Sovereign AI Operating System @delentia-labs/delentia-mcpStop rogue AI-agent tool calls before they run: deterministic policy gate + audit digest.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Warda @artykomarkets/wardaEconomic authority for autonomous agents on Kaspa L1. Never holds a key.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Neon Zero-Trust Gateway @ansarii/zero-trust-gatewayZero-Trust MCP gateway securing internal database tools behind an API key firewall.22% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Kanonik @kanonik/kanonikGovernance runtime for compliance: verified, human-approved writes to a tamper-evident record.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Delta Witness @15998194110/delta-witnessPaid Capture and Guard tools for public-source observations before autonomous actions.13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ratchet — effect gate @ratchetgate/ratchetYour agent asks before it acts, so the same real-world action is attempted at most once.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Tollary Agent Transaction Guard @p-e/agent-transaction-guardLocal fit-check and safe integration guidance for non-custodial Base USDC agent transactions.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memory Pulse @t-crew/memory-pulseCorrections that outlive the session. A guard blocks the edit that writes the old value back.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Channel @amkentech/agent-channelOne identity across Claude Code, Codex, Cursor, Gemini, Windsurf: shared inbox and handoffs.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
