- Proof @toremlabs/proofGovern your AI coding agent: frame the work, review the changes, keep a signed decision record.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Moneo @moneolabs/moneoA guarded wallet for AI agents on Robinhood Chain: a spending policy runs before every signature.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Rails @jaimenbell/rails-mcpDefault-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- AgenticRail Gate - sequence enforcement and verifiable audit receipts for AI agent compliance @agenticrail/gateDeterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Commerce Guard @fxjim/agent-commerce-guardPolicy review and purchase discovery for AI-agent commerce actions.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- BailingHub for Business Operations @bailinghub/bailinghub-governanceLet AI agents query and operate business systems with authorization, approval and audit trails.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ghostlink @bgorzelic/ghostlinkSandboxed repo access for coding agents: search, read, patch, run, git -- confined to a repo root.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- BountyVerdict Agent Decision Tools @mimirs402/bountyverdictFree selector plus read-only GitHub bounty, agent harness, Actions, flake, and MCP drift decisions.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Guard @kavachh/agent-guard-mcpGit-aware safe file ops for AI agents: delete anything except git-tracked source code.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- BountyVerdict Agent Decision Tools @cristianmoroaica/bountyverdictRead-only GitHub bounty, agent harness, Actions failure, flake, and MCP tool-drift decisions.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Ai Consensus @thestevenjohnstone/ai-consensusStanding review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- UpToCode @ddyrich72/uptocodeEvidence-backed architecture-quality analysis for Python agent applications.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- ODGS @metricprovenance/odgs-mcp-serverODGS governance enforcement — validation, regulation compilation, drift detection, signed S-Certs.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Understand Anything - MCP @uamcp/ua-mcpA powerful MCP server for codebase architecture analysis and automated governance.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Panella @panellatech/panellaGoverned, self-hosted memory for AI agents: writes queue until a named person approves.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Phaedo @phaedo-labs/phaedo-mcpCarry your Phaedo cognitive fingerprint into any MCP client: inject, consult, escalate, sign.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Repotector @dir-ai/repotectorThe repo guardian AI agents handshake with before they touch your code.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Whetstone @cyberelf/toolsVerifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Toolbox @solhammer/agent-toolbox26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- A2A TrustGate @jyswee/a2a-trustgateA2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 50 tools.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Heartwood Memory — governed memory for AI agents @jermayne36/heartwood-memoryHeartwood Memory — governed AI agent memory; signed provenance. BUSL-1.1; not OSI open source.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- kcp-agent — KCP navigation planner @cantara/kcp-agentDeterministic, fail-closed planner for KCP knowledge manifests: kcp_plan, kcp_load, kcp_validate.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- kcp-harness — KCP compliance proxy @cantara/kcp-harnessMCP compliance proxy between agent and tools: deterministic governance, fail-closed, audit trail.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Authoryze @authoryze/authoryzeGive your AI agent a spending limit: approval controls and single-use virtual cards.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
