搜索「Policy Enforcement」的结果

io.github.presidio-v/presidio-hardened-x402-mcp

x402 的支付前 PII 筛查器——在智能体签名前捕获邮箱、SSN、姓名。

io.github.svayatta/agent-custody

MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt

io.github.zyvorai/kairon

Inspect Kairon VMs, network policy and VM-edge flows from an agent. Read-only by default.

io.github.polymatx/opsgate

The safety gate between AI agents and your servers: typed, policy-checked, audited ops tools.

com.ai-rete-rag/ai-rete-rag-mcp

从政策文档中编写规则，再做判定：由 Rete 引擎给出裁决，LLM 负责解释原因。

io.github.nethinwei/sql-mcp-server

Controlled SQL access gateway with policy, cost limits, tenant isolation, and safe tools.

ai.getmarrow/marrow

Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.

io.github.XAGI-Lab/melra

Local MCP runtime for policy-governed, verified agent actions with durable receipts.

io.github.GuardBee/security-proxy

MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log

io.keyban.prod.mcp/agent-wallet

Give an AI agent its own blockchain wallet: balances, USDC transfers, x402 payments under policy.

com.mailbuttons/mcp-server

面向 AI 智能体的可治理邮件（Mailbuttons / mbag.ai）：沙箱收件箱、策略闸门与审计日志。

io.keyban.mcp/agent-wallet

Give an AI agent its own blockchain wallet: balances, USDC transfers, x402 payments under policy.

io.github.AIops-tools/ai-guardian

受治理的本地 LLM 可观测性：模型策略、提示词扫描、捕获代理，21 个工具。

io.github.bugiiiii11/rein

Spend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.

io.github.Yacine-ai-tech/agentkit

Governed MCP server: YAML-declared tools, typed effects, policy-gated and audited calls.

io.github.WYRE-AI/action1-mcp

Action1 MCP 服务器——经 REST API 提供终端清单、补丁可见性与策略自动化。

io.github.WYRE-AI/spamtitan-mcp

SpamTitan 邮件安全的 MCP 服务器，提供隔离区、黑白名单与策略管理。

com.altmetric.mcp/altmetric-mcp

Altmetric API 的 MCP 服务器——追踪新闻、政策、社交媒体等的学术研究关注度。

io.github.rowstile/rowstile

Check, test, prove and review a rowstile policy: access rules for Postgres row-level security

io.github.lyf-wxy/spomory

Explainable graph-retrieval memory engine with an RL-trained management policy.

com.scopeblind/protect-mcp

为智能体工具调用提供 fail-closed 的 Cedar 策略闸门与 Ed25519 签名回执，任何出错即拒绝。

io.vulnify/mcp

Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.

io.github.aggrete/aggrete

MCP policy proxy: enforces a code of conduct across connectors before the upstream is called.

io.github.RostislavMatov/mcpcut

Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval