- MCP Output Firewall @tangfei7777-cell/mcp-output-firewallThree-layer firewall for MCP: content, egress and action policy. Proxy or server.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Deadlatch @diabloluo/deadlatchLocal advisory pre-trade risk gate for agents. Never places orders.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Project Memory @dankaro-projects/project-memoryLocal decisions, evidence, outcomes and reviewed lessons with bounded retrieval and an HTML viewer.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Proctor @louissarvin/proctorHuman oversight for AI agents: block a tool call on a verified human, with on-chain proof.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- WPGuard MCP @cgallic/wpguard-mcpWordPress edit previews, scoped correction checks, and change records for trusted operators.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- ReadyAgents @readyagentsdev/readyagentsLocal YAML/JSON agent workflow CLI with approvals, resume, and optional stdio or loopback MCP HTTP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Interop Runtime @praket7/agent-interop-runtimeLocal MCP runtime for coordinating Freebuff, Codex, OpenCode, Claude Code, and Cursor agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 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.
- 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.
- Living Stack Community @equinoxaifinance-rgb/living-stackFree seven-tool proof loop for scoped authorization, outcome receipts, and evidence-bound claims.5% 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.
- 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.
- 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.
- 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-pulseGive any agent self-improving memory you can trust in production. Built-in memory security.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Skill Sec @sudo-ai-git/mcp-skill-secAudit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Verify Claim @sudo-ai-git/mcp-verify-claimForce evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Residue Evidence @fantasyce/agent-residue-evidenceReport local task-scoped test and build residue without cleaning resources.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- pgops @arzharch/pgops-mcpSafe, audited PostgreSQL operations for AI agents: queries, migrations, EXPLAIN, containers3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
