- Crabeye Bridge @crabeye-ai/crabeye-mcp-bridgeOne MCP connection for all your tools — with discovery, namespacing, and execution policies.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Sidclaw Governance @vladuzh/sidclaw-governance-mcpGovernance proxy for MCP servers — policy evaluation, human approval, audit trails.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Orbit @constellation-works/orbitOrbit's local-first task and workflow registry for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Aegis @getaegis/aegisCredential isolation for AI agents. Inject secrets at the network boundary.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Assay @rul1an/assayThe firewall for MCP tool calls. Block, audit, replay with evidence bundles.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.13 GitHub stars.
- Stepgate @chaarangan/stepgateAgents can't skip steps: runs gated stepfiles on the client's own model.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
- Infrabroker @luisgf/infrabrokerSSH & Kubernetes access broker for AI agents; the model never touches a credential.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.13 GitHub stars.
- Assay MCP Server @rul1an/assay-mcp-serverPolicy-enforcing MCP proxy with portable evidence output.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.13 GitHub stars.
- x402check @caiovicentino/x402checkRisk-check counterparties before an AI agent pays; pay x402 resources only after a verified allow5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- Behavior Runtime MCP @putervision/behavior-mcpIn-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- Aletheia Runtime Safety & Scope Creep Filter @vikasny30/aletheia-mcpDeterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
- SkillTotal @skilltotal/skilltotalDeterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
- Lingua Universale MCP Server @rafapra3008/lu-mcp-serverVerify AI agent communication with session types and formal proofs6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
- Kagan @kagan-sh/kaganAI-powered Kanban TUI for autonomous development workflows with agent orchestration5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
- MobiLoop @enessubass/mobiloop-mcpGuarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.11 GitHub stars.
- Klarion @0x1adi/klarionSecret scanning for AI agents: rules and entropy find candidates, a model decides which are real.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.11 GitHub stars.
- Scopeblind @tomjwxf/scopeblind-mcpScan, protect, and monitor APIs from AI coding tools. Device-level rate limiting.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Agenticorg @mishrasanjeev/agenticorgRepository MCP adapter for company-scoped workflow candidates and conditional API discovery.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Trentina @crunchtools/trentinaSecure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Glassbox Framework @thebarmaeffect/glassbox-frameworkRuntime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Mcacp @oortonaut/mcacpMCP-to-ACP bridge — let any MCP client drive ACP coding agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Aperion Shield @aperionai/shieldLocal guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.11 GitHub stars.
- SchemaBrain @arun-kc/schemabrainThe trust and intelligence layer between AI agents and your database.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Writbase @writbase/writbaseMCP-native task management for AI agent fleets with scoped permissions and provenance.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
