- Grantex @mishrasanjeev/grantexOAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.33 GitHub stars.
- AgentGate @agentkitai/agentgateHuman-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.33 GitHub stars.
- JanuScope @giancarloerra/januscopeLocal MCP proxy for tool restrictions, response redaction, audit logs, and database schema context.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.32 GitHub stars.
- Graqle @graqle/graqleDev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
- agent-bom @msaad00/agent-bomSecurity scanner and graph for agentic infrastructure — agents, MCP, runtime, and blast radius.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.31 GitHub stars.
- HealthClaw Guardrails @aks129/healthclaw-guardrailsGuardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.31 GitHub stars.
- Gnt @gnt-ai/gntGit-native policy layer for AI agents: check_action verdicts against rules approved via PR.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.30 GitHub stars.
- Janee @rsdouglas/janeeSecure secrets proxy for AI agents — manages API keys so agents never see raw credentials.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.30 GitHub stars.
- MCP Memory Gateway @igorganapolsky/mcp-memory-gatewayPre-action gates that block AI agents from repeating known mistakes.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.28 GitHub stars.
- RLHF feedback loop @igorganapolsky/rlhf-feedback-loopRLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.28 GitHub stars.
- Humane Proxy @vishisht16/humane-proxyAI safety middleware — detects self-harm and criminal intent in LLM prompts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.28 GitHub stars.
- RepoRelay @lukie-81/reporelayBounded local MCP access to one approved repository for AI read/search and structured handoffs.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.27 GitHub stars.
- KittyClaw @ekioo/kittyclawDrive KittyClaw, a self-hosted agent-fleet kanban, from any MCP client (embedded /mcp endpoint).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.27 GitHub stars.
- Rigour @rigour-labs/rigourLets coding agents review their change, find an existing helper, and recall the team's lessons.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.27 GitHub stars.
- CTRLRun Operator @ctrlrun/ctrlrun-mcp-operatorAnswer CTRLRun approvals from an MCP client: list what is held, inspect it, grant or deny.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.26 GitHub stars.
- Audrey @evilander/audreyLocal-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.26 GitHub stars.
- Roast My Design System @gregkozakiewicz/roast-my-design-systemAudit your Design System and serve your Agent the rules that keep AI-written UI on-system.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.25 GitHub stars.
- Speclock @sgroy10/speclockAI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.25 GitHub stars.
- Delego @delego-dev/delegoIntent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.25 GitHub stars.
- McpMux @mcpmux-io/mcp-muxMcpMux — configure MCP servers once, connect every AI client through one local gateway.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.24 GitHub stars.
- Mneme Decision MCP @mnemehq/mnemeLocal MCP server for architectural decisions, traceability, and non-authoritative proposals.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.24 GitHub stars.
- Fable Mode @rex-codebase/fable-modeMechanical write gates, evidence receipts, and adversarial review for AI coding agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.24 GitHub stars.
- Delimit — Keep the state. Change the model. @delimit-ai/delimit-mcp-serverKeep the state. Change the model. Shared context and a multi-model panel across coding assistants.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- McpMux @mcpmux/mcp-muxMcpMux — configure MCP servers once, connect every AI client through one local gateway.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.24 GitHub stars.
