groundtruth
v7.5.0
io.github.rm-rf-prod/groundtruth
实时文档 MCP 服务器:598+ 个库、证据核验的答案、代码审计、代码片段与调度。
“Security Audit” 共 682 个结果
v7.5.0
io.github.rm-rf-prod/groundtruth
实时文档 MCP 服务器:598+ 个库、证据核验的答案、代码审计、代码片段与调度。
v0.7.0
io.github.KryptosAI/mcp-seatbelt
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
v0.1.1
io.github.mcpcustoms/mcp-customs
Inspect an MCP server for common security risks before you install it. Offline, zero telemetry.
v0.5.0
io.github.ebeirne/lians
为 AI 智能体提供双时态记忆,支持时点回溯与防篡改的审计历史。
v0.1.2
ai.thrain/spotlight
本地 PDF 无障碍审计:可机器校验的 PDF/UA 基础项(ADA/EAA/508),无需上传。
v0.6.0
io.github.forkflux/forkflux-mcp
为 AI 辅助工程团队提供自托管的多智能体协作与审计层。
v2.7.4
io.github.sarveshsea/memi
Memi 是面向编码智能体的只读设计工程审计与技能层。
v0.8.0-beta.10
io.github.Arakiss/nahuali
Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
v0.4.4
io.github.knowledgepa3/gia-mcp-server
运行时 AI 治理:决策门禁、人工审批、哈希链审计与合规映射。
v0.2.0
io.github.heidihelena/vahtian
Freeze a corpus, check it for drift, keep a hash-chained audit ledger. Local-first, stdlib-only.
v0.71.3
io.github.zyx77550/sparda-mcp
AI 负责写,SPARDA 负责证明:为 AI 的改动提供确定性的离线安全关卡。
v1.0.5
io.github.adamsjack711-ux/pkgxray
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
v0.1.13
io.github.VladUZH/sidclaw-governance-mcp
MCP 服务器的治理代理——策略评估、人工审批、审计留痕。
v1.9.0
io.github.SakuraCianna/agentic-sdlc-mcp
Agentic SDLC governance and security controls for AI coding agents working with GitHub.
v0.3.1
io.github.hs3434/sandbox-env-mcp
Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.
v0.2.1
io.github.bobaba99/motionlint
Catch bad animations before they ship. Deterministic motion audit + vision-LLM design review.
v0.1.3
io.github.KN0WBOT/clavis
面向 AI 代理的加密凭据保管库,支持 OAuth 自动刷新、限流与审计日志。
v0.9.1
io.github.jonnybottles/patch-tuesday
Query Microsoft Patch Tuesday security updates (MSRC) with EPSS and CISA KEV enrichment
v1.36.1
io.github.KryptosAI/mcp-observatory
MCP 安全扫描器,支持 CI 原生测试、攻击模拟、健康评分与 SARIF 输出。
v2.0.0
io.github.IPGeolocation/ipgeolocation-io-mcp
IP 定位官方 MCP 服务器:安全情报、ASN、滥用信息、时区、天文与 user-agent 解析。
v0.1.0
io.github.jaimenbell/rails-mcp
Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).
v0.1.1
io.github.farukkolip/instapdown-mcp
16 Instagram creator tools: downloaders, engagement audit, hashtags, hooks, best-time, calendar.
v1.2.3
com.correctover/mcp-server
MCP 运行时安全:22µs 校验、97% 自愈,可检测 RCE、SSRF 与凭据劫持。
v1.5.0
io.github.edgarfloresguerra2011-a11y/marketnow
MCP marketplace with 8,845 security-audited skills. 9-layer Sentinel audit + ATC trust cards.