- Sshboard @meta-taro/sshboardAn AI agent reads your server over the one SSH session you are already watching.Not assessed yet.Runs on your machine, installed from a package registry.
- Abe @flowinfosystems-index/abeFree, local check before an AI agent acts: your rules return ACT, BLOCK or ESCALATE.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Atlas @corpussanctum/atlas-mcpPre-action authorization for AI agents: permit, deny or escalate against a signed delegation chain.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentKit @yacine-ai-tech/agentkitGoverned MCP server: YAML-declared tools, typed effects, policy-gated and audited calls.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Datumline Agent Guard @datumline/agent-guardChecks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Phocinae MCP @phocinae/phocinae-mcpLocal Phocinae decision-engine MCP stdio server: fail-closed approval gate + classify/route/score.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Local Workspace @peter4leadson/local-workspace-mcpBounded, read-oriented filesystem, git and named-task tools over authorized workspace roots.Not assessed yet.Runs on your machine, installed from npm.
- macOS MCP Server @deploymenttheory/macos-mcp-serverLocal macOS 27 desktop automation through MCP on Apple silicon.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- AegisGate MCP @aegisgatesecurity/aegisgate-mcpSecure MCP server framework with 23 security layers and ML threat detection. Zero deps.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Pranaxis Gateway @anaciber/pranaxis-mcp-gatewayConsistency verdicts for MCP tool calls: no two agents consume the same resource version twice.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- IRL Gateway @norve-labs/irl-gatewayAn AI agent's trading mandate it can't break: checked before every order, reasoning sealed in IRL.Not assessed yet.Runs on your machine, installed from PyPI.
- Vibe Gate @mustafacagri/vibe-gate-mcpAdversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlockNot assessed yet.Runs on your machine, installed from npm.
- gutsy @kouhxp/gutsyLocal gut check before risky agent actions: calibrated safe/intended probabilities, no API calls.Not assessed yet.Runs on your machine, installed from PyPI.
- chat-tool-ui-preview @gridhra/chat-tool-ui-previewPreview a chat post before an agent sends it: text, mentions, destination, warnings. Never sends.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- MCP Security Guard @petrovicistefan/mcp-security-guardAudit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).Not assessed yet.Runs on your machine, installed from npm.
- Brainy @memokar/brainyShared knowledge base + task queue so Claude, ChatGPT and other agents can work together safely.Not assessed yet.Runs on your machine, installed from Docker.
- Rein @bugiiiii11/reinSpend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Bridgistic @wordpressistic/bridgisticConnect Claude to WordPress safely: signed requests, scoped keys, approvals, logs, snapshots.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AtlaSent MCP Server @atlasent-io/mcp-serverAtlaSent for AI agents: with an API key, actions wait for approval with signed proof. No key: demo.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Gate Authority Network @projetxana/gate-authority-networkLive cross-domain authority-state resolution for delegated agents through MCP.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- mcpgawk @gawk-dev/mcpgawkMeasure MCP servers, pin the approved tool surface, refuse calls to tools that changed. Local-first.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Confirm @les-k/mcp-confirmAn MCP server whose confirmation cannot be replayed against a different call.Not assessed yet.Runs on your machine, installed from PyPI.
- Pg Readonly @les-k/pg-readonly-mcpA read-only Postgres MCP server that parses SQL rather than pattern-matching it.Not assessed yet.Runs on your machine, installed from PyPI.
- IAF Agent Bridge @francescoveryra-dot/iaf-agent-bridgeMCP server that sends work to Cursor Agent over ACP and returns the session id needed to continue.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
