Koma Gate MCP
v0.1.1
io.github.swnotmetal/koma-gate-mcp
Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
“Prompt Injection” 共 270 个结果
v0.1.1
io.github.swnotmetal/koma-gate-mcp
Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
v1.0.0
ai.b77/ai-media-studio
从一句聊天提示词生成图片、视频、旁白与字幕。
v0.1.2
io.github.Syedomershah99/being-human
Learns your writing voice from your own prompt history, then makes the model write like that.
v0.1.21
io.github.sgateway/s-gw
Keep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.
v1.0.0
work.agentexchange.tooldrift/monitor
Check if an MCP server tool changed or hides injection patterns before you trust it.
v0.45.4
io.github.Graphiker-Australia/stipend
Non-custodial USDC wallet on Base with spending limits enforced in code, not in a prompt.
v0.1.4
io.github.RudrenduPaul/truthroute
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
v1.3.0
io.github.mlawsonking/agent-firewall-mcp
AI 代理的输入输出安全:已知模式的提示注入与混淆扫描、URL/IP 检查与密钥识别。
v1.3.0
io.github.mlawsonking/email-guard-mcp
面向 AI 代理的邮件安全:入站扫描提示注入与钓鱼,出站检查密钥泄露。
v1.3.0
io.github.mlawsonking/code-guard-mcp
扫描 AI 生成代码的安全问题:注入、SSRF、密钥泄露、弱加密与不安全的反序列化。
v0.1.0
io.github.alialrikabi313/hares
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
v0.13.0
io.github.tiagosilva07/zyrax-guard
审计 AI 智能体配置中的提示注入与可疑 MCP 服务器,并对第三方依赖包进行甄别。
v1.1.4
io.github.vpatser1/mcp-server-security-scanner
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
v1.1.1
io.github.jamesmontemagno/ohmyposh-configurator
MCP server for creating, validating, and exporting Oh My Posh terminal prompt configurations.
v2.2.0
com.meertrack/mcp-server
竞争情报——每周追踪竞品发布了什么。8 个工具,3 套提示词工作流。
v0.2.5
io.github.Explorer-64/imagcon-mcp
Generate PWA icon sets and iOS splash screens from a text prompt or an existing image.
v0.1.0
io.github.Hiroshi-Ichiyanagi/kagami
Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.
v0.1.3
io.github.federicodeponte/openpaper-mcp
自主研究引擎:从一个提示词自动完成调研,产出带完整引用的学术论文,经 MCP 提供。
v0.1.0
io.github.hzy9981/aviation-accident-analysis
Aviation accident report parsing and prompt generation service under the SHELL framework.
v2.2.0
io.github.bystray/gonka-mcp-server
为 AI 智能体提供第二意见:一次调用即可让多个在线 Gonka 模型带角色回答同一提示词。
v1.0.1
io.illumora/craft
Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.
v1.4.0
io.github.dir-ai/voyager
Cited, OSV-gated, injection-hardened web briefs for coding agents. Verified, never raw web.
v0.1.0
app.web.mindset-502113/mindset
对 MINDSET 品牌策略主题数据库的语义检索,并附其系统提示词。
v0.1.1
io.github.galavoxx/phaedo-mcp
把你的 Phaedo 认知指纹带入任意 MCP 客户端:支持风格注入与决策咨询。