搜索「Policy」的结果

io.github.Guffawaffle/lex

面向 AI 智能体的情景记忆与架构策略层，包含 Frames、Atlas 与 Policy。

LastLook 行情数据

io.smithery.zev.lastlook-data

LastLook Data 为 AI 智能体提供美国金融市场的实时数据：国债收益率（2 年、10 年、30 年）、房贷利率、联邦基金利率、CPI、失业率、GDP、WTI/布伦特原油、天然气以及 G10 汇率。还包含派生指标：收益率曲线利差（2s10s、3m10y）及倒挂信号、萨姆规则衰退指标、联储政策利差（EFFR 与 IORB），以及临近的 FRED 经济日历。数据来自 FRED 和 ECB。通过 Base 上的 x402 按次付费——无需账号、无需 API key、无需订阅。

agentdevx API 网关

io.smithery.mirajmahmudul57.agentdevx

安全调用任意 API 的 AI 智能体网关。一次调用完成智能体初始化、发现工具、执行 OPA 策略并自动注入凭据。 ## 特性 - 一次调用即可引导智能体启动，配 Ed25519 身份 - 工具注册表，支持导入 OpenAPI - OPA 策略执行 - 加密凭据库 - 分档每日限额（free/starter/pro/scale） ## 快速开始 POST https://agentdevx.onrender.com/agents/v1/bootstrap {“public_key”: “<你的 ed25519 公钥十六进制>”}

Govbase

io.smithery.govbase.govbase

Govbase provides U.S. federal policy data — search bills, executive orders, look up Congress members and voting records, browse narrative story bundles, and get civic info like representatives and polling locations by address.

密码强度检查 —— 熵值与破解耗时

io.smithery.axel-belfort.password-strength

面向 AI 智能体的密码强度评估 API。给出 0-100 评分、熵值比特、预计破解时间（暴力破解与字典攻击）、模式识别结果以及可落地的改进建议。工具：security_check_password。适用于密码策略执行、用户注册校验或安全审计，返回机器可读的强度数据以支撑自动化决策。返回：{score, entropy, crackTime, tips[]}。无需 API 密钥——在 Base L2 上以 x402 微支付 $0.001/次。

邮件送达率审计 —— SPF/DKIM/DMARC 检查

io.smithery.axel-belfort.email-deliverability

面向 AI 智能体的邮件送达能力审计 API。分析任意域名的邮件身份验证：SPF 记录校验、DKIM 选择器检查、DMARC 策略分析、MX 记录健康度，并给出 0-100 的综合送达评分与按优先级排列的修复建议。工具：email_audit_deliverability。用于审计邮件基础设施、排查投递问题或在批量发送前检查域名信誉。注意：此项检查的是域名配置，单个邮箱有效性校验请改用 email_verify_address。返回：{score, spf, dkim, dmarc, mx, recommendations[]}。无需 API 密钥——在 Base L2 上以 x402 微支付 $0.005/次。

io.github.HamdiM99/intentplane

Gateway in front of MCP tools: critical arguments are checked against trusted sources and a policy.

io.github.Diogoup26/mcp-x402

Evidence-backed pre-purchase checks for offer terms, seller trust and policy compliance.

io.github.GuardBee/security-proxy

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

io.github.sepehr071/cbi-mcp

Read-only Central Bank of Iran (cbi.ir): official FX rates, inflation, policy rates, news.

io.github.nvdigitalsolutions/nvoos-mcp-gateway

Streamable HTTP MCP gateway for NV oOS fleets — one API key, namespaced tools, quotas and policy.

com.handbookhub/handbookhub

Search and read saved employee handbooks with scoped, read-only access and policy source links.

io.github.om-tajne/pkgdiet

Dependency policy and MCP server to stop AI coding agents from installing risky npm packages.

io.github.Benji18sport/agent-trust-firewall

Free pre-action policy checks and data cleaning for autonomous AI agents.

com.ngrok/mcp

Manage ngrok from your agent: endpoints, domains, and traffic policy.

io.keyban.mcp/agent-wallet

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

ai.achromat/mcp-server

Recall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.

site.star365/aic

Find AI-agent sellers, read AIC supply and join policy. Read-only; buying is done client-side.

ai.getmarrow/marrow

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

xyz.paystage/preflight

Evaluate x402 PaymentRequired against a local spending policy before an agent pays

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。

cloud.wavehouse/mcp

浏览、查询并管理你托管的 WaveHouse + ClickHouse 项目（schema、管道、策略）。

io.github.rowstile/rowstile

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

io.github.svayatta/agent-custody

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