搜索「Policy」的结果

io.github.r33drichards/mcp-js

Run JavaScript and TypeScript in sandboxed V8 isolates with policy-controlled host capabilities.

io.github.commit-check/commit-check-mcp

校验提交信息、分支名、作者信息、推送安全性与仓库状态。

io.github.agentwares/agentguard

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

io.github.eminegurcu/auditsocials-compliance-mcp

Pre-publish policy check for AI-generated social & ad content across 8 platforms.

ai.gateco/gateco

面向 AI 系统的权限感知检索：按策略执行的组织知识访问控制。

io.github.Shrike-Security/shrike-mcp

管控 AI 智能体的行为：工具调用、SQL、命令与文件在运行前均按策略检查。

io.github.4hmetuyar/security-proxy

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

io.github.withwrit/writ

Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.

io.github.szl-holdings/hatun-mcp

Governed MCP gateway: policy gate on every tool call, hash-chained DSSE receipt on every result.

io.github.AvenueDAdmin/writ

Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.

io.github.caseone115/claimgate-kit

Set up a publish gate for AI-assisted marketing copy: policy, evidence folder and CI job.

ai.satohub/kit

Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.

io.github.trycoin-ai/agentrisk

为 AI 交易智能体提供风险护栏：智能体提出方案，由你的策略做决定。

io.github.malkreide/swiss-snb-mcp

SNB 数据门户：汇率、资产负债表、政策利率、SARON 与货币供应量。

io.github.jl-codes/platformio-mcp

Build, inspect, flash, and monitor PlatformIO firmware projects with policy-controlled tools.

io.github.DLJRealty/guesty

Guesty MCP 服务器，43 个工具全部免费：预订、房源、客人、消息、定价、营收。

io.github.cohoststr/cohoststr-mcp

CohostSTR: MCP server for Guesty. 43 read/write tools, free. Grounded replies, policy screen.

io.github.giupy997/cra-agent

Lets an agent pay for x402 APIs in USDC on Arc, under a spending policy it cannot change.

io.github.SirMacke/adsense-mcp

Read AdSense Management API v2 accounts, inventory, payments, policy, and reports through MCP.

io.github.ciceroyang/agentgate

Read-only evidence for the tools agents run: MCP server records, coverage and policy.

io.github.MNKIAgentOS/mnki-mcp

MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.

io.github.iversonwuwei/ratchet

Read-only tools to inspect your agent setup: list MCP servers, flag unpinned ones, test a policy.

io.github.dev-prathap/attest-proxy

Zero-code proxy: policy, human gate, read-back and a hash-chained ledger for any MCP server.

io.github.dev-prathap/attest

Decide by policy, gate behind a human, verify by read-back, record a hash-chained ledger.