- ddflow @delian/ddflow-mcpWork-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- presign-guard wallet @fizzl13/presign-guard-walletAgent wallet with limits: pays x402/MPP on Base, Solana, Tempo, XRPL and Algorand; phone approval.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mandare @mandarelabs/mandareVerify an agent fleet's tamper-evident ledger, check budgets, kill a runaway agent. Local-first.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- TWZRD @twzrd-sol/twzrd-mcpAuto-pay MCP for the TWZRD Trust API: free preflight + x402-paid Solana trust intelNot assessed yet.Runs on your machine, installed from PyPI.
- agentpay @hellotravisss/agentpayEnforced budgets for agents paying x402 APIs: the gateway holds the wallet, not the agent.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Rail @tstockham96/rail-mcpBudgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default.Not assessed yet.Runs on your machine, installed from npm.
- amu-pgvector @sangaraju1988/amu-pgvectorLineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security.Not assessed yet.Runs on your machine, installed from PyPI.
- Lagaam @lagaam-ai/lagaamStops an agent's Trino or Pinot query before it runs if it costs too much or reads outside its grantNot assessed yet.Runs on your machine, installed from PyPI.
- Guard @codapult/guardLocal-first architecture guardrails and project context for JS/TS AI coding agents.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- SynomosAI Governance MCP @medxpert-org/ubic-governance-mcpAI governance MCP: A3 scorecard, ISO 42001 evidence templates, compliance checklist, gov_scan.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- chargehand @egoushka/chargehandRuns coding-agent workers on a codebase question; every claim in the answer carries evidence.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- Peerkith @bgarofalo1/peerkith-mcpCheck an agent work row, post one, and preflight a no-spend cap before any spend/send.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Quirna @quirna/mcpAsk a human before your agent acts: approval requests decided on a phone.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Reins @r2rlabs/hyperliquid-reinsRisk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Runner MCP @blacksp1d3r/runner-mcpSelf-hosted MCP for controlled AI development and staging without a general-purpose remote shell.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- opencode subagents @sebstaq/opencode-subagent-mcpRun Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MCP Write Gate @goran-revops/mcp-write-gateSits in front of any MCP server. Reads pass, writes are checked against your lists.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- FluxGit @fluxgit-hq/fluxgit-mcp-serverSafety-first Git MCP server: rich read tools plus human-approved FluxGit operation proposals.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.
- Aga @attestedintelligence/aga-mcp-serverVerifiable decision records for AI agents: signed receipts for calls to its own governed tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- BRYDGE @brydge-ai/brydgeChecks whether an agent's actions actually happened, against the destination's own records.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Yault AESP @yault/aespCrypto payments for the agent economy — policy-gated vault operations under human control9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Oasis @p31ca/oasis-mcpAgent-native CLI: provenance, cost governance, and execution contracts for AI agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Continuity Gateway @zerohourzulu/continuity-gatewayLocal MCP gateway for approved jobs, current agent permissions and durable retry inspection.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Vizier Guard @vassiliylakhonin/vizier-guardDeterministic authorization and security guard for AI agent actions with signed receipts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
