- Declaw AI MCP @declaw-ai/mcp-serverSecure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Countersign @countersign-network/countersignKill switch + spend guard for AI agents that spend money, across every wallet vendor at once.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- commit-check MCP @commit-check/commit-check-mcpCommit policy as code for AI agents: check commit messages, branch names and authors before a push3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Attest @chudah1/attest-mcpCredential enforcement middleware for MCP servers — verifies scoped tokens on every tool call4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- PromptSpeak Governance @chrbailey/promptspeakPre-execution governance for AI agents. Validates tool calls before they execute.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Tripwire @bonesdefi/tripwireSecurity gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Queryshield @bch1212/queryshieldSecure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- keyward @arturayupov/keywardLocal encrypted secret broker for AI agents: request keys by name, approve each use over MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Trust @agntor/trustTrust layer for AI agents: identity, guard, redact, escrow, and x402 payments.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Impact preview @agent-polis/impact-previewImpact preview for AI agents - see what changes before any action executes.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- AgentLoopKit @abhiyoheswaran1/agentloopkitRead-only MCP server for AgentLoopKit tasks, policies, reports, handoffs, and status.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Tetrad @samoradc/tetradQuadruple consensus MCP server for code validation using Codex, Gemini, and Qwen6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Wisegit @sandip124/wisegitExtracts decision intent from git history and protects intentional code from AI modification.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Agentpay Sentinel @rumblingb/agentpay-sentinel-mcpSecurity guardrails for AI agent payments7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Agentguard @mukundakatta/agentguardNetwork-egress firewall for agent tools: check URLs against a declarative policy.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Credence — Epistemic Guard @lakshmi-chakradhar-vijayarao/credenceEpistemic guard for AI coding: tracks uncertain values and blocks writes until verified.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Chain Signer @kevthetech143/chain-signerSecurity suite for AI agents: flag drains, permit-phishing & risky actions before signing.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Guardrails @expertvagabond/guardrailsAI Agent Guardrails MCP server - security layer5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Cloaked Agent @cloakedagent/cloakedTrustless spending accounts for AI agents on Solana with on-chain enforced limits.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Tidebase @blueprintlabio/tidebaseInspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- VantaGate @aderix/vantagate-mcp-serverVantaGate MCP Server & OpenAPI integration - Human-in-the-Loop for AI Agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Pop Pay @100xpercent/pop-payRuntime security for AI agent commerce. CLI + MCP server blocks hallucinated purchases.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Ai Agent Firewall @fidacy/ai-agent-firewallEvery agent action watched, every money-moving one gated, every verdict independently verifiable.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Marchward MCP @marchward/mcp-serverRuntime authority for AI agents: credential mediation, spend cap, approval gates, audit log.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
