- p-e relay (remote) @it-start/relay-uiRemote MCP access to the p-e relay store. Reads are open; writes and waits are signed.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- vaultguard @ashishrao-4/vaultguardAI agents use your Obsidian secrets by name — values never reach their context.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- VERAX @verax-ai/veraxThe body an agent asks before it acts: decide, approve, and keep a signed record on your machine.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- VPS Guardian @murzirius/vps-guardian-mcpSecure SSH bridge for AI agents to observe and safely administer Linux VPSs.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Collar Guardrail — Pre-Trade Risk Layer @aiguardrail/backendDeterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Lex @smartergpt/lexEpisodic memory, Frames, Policy Neighborhoods, and policy enforcement for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PitBridge @pitbridge/pitbridgeLocal-first MCP bridge for NinjaTrader 8 behind a deterministic guardrail engine.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- FGAC.ai: Multiple Gmail Accounts, Google Sheets & Docs @fgac/fgacMultiple Gmail accounts, editable Google Sheets & Docs for AI agents. Deny-by-default access rules.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Mandate Verification @api-disk-integrations/agent-mandateVerify a proposed action against a signed Agent Mandate without executing or mutating accounts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AION SUPREME Agent Temple @wisemankonstantin-droid/aion-agent-coreVerified agent routing with bounded discovery, outcome evidence and economic policy.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 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.
- HallucC — Hallucination & Safety Guardian @fredyee/halluccFact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Governance @coderifts/api-governanceSigned, offline-verifiable contract-change authorization. Only a granted change can proceed.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 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.
- Blindoracle @craigmbrown/blindoracleTrust + counterparty-risk layer for x402 A2A trades: reputation, pre-hire check, escrow, disputes14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Proofable MCP @proofable/mcpContext and control for any AI. Agent identity, scoped access, and proof across tools.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- 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.
- pendnt @pendnt/pendntHuman approvals, notifications, inbound webhooks, wake-ups for headless agents. Free trial: /try8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- 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.
- AgentLedger @entradox/agent-ledgerMeter, cap, and block AI agent spend before the provider is charged.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 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.
- Agent Control @agent-control/agent-controlFree agent directory and job board. List your agent free: give it agent-control.net/skill.md23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
