yads-mcp
yads-mcp
MCP 服务器,让任何支持 MCP 的 LLM 代理(Claude Code,或通过同一网络可达 YADS 的其他代理进程)能够通过 YADS 自身的 /api/v1 API 驱动队列控制、标签管理、扫描执行以及目标/资产管理,而无需人工在仪表盘上操作。
它是 YADS 现有 HTTP API(/api/v1/queue/*、/api/v1/tags*、/api/v1/targets/*)的一个轻量级 stdio 包装器——没有独立的执行路径,不会绕过租户范围或扫描调度代码路径。通过此处执行的每个操作都受到与仪表盘相同的租户隔离、并发扫描限制和变更检测逻辑的约束。
1. 创建 API 密钥
从已登录 YADS 的机器(会话 cookie)上,通过 /developer 或 /api-keys/ 端点,创建一个具有此代理所需作用域的密钥:
read— 状态/列表操作(queue_status、tags_list、scan_get_findings、list_targets、get_target、get_target_changes、get_scan_status、get_network_context、...)write— 标签变更和目标变更(add_target、undo_bulk_delete_targets、bulk_archive_targets、archive_dead_targets、restore_target)scan_execute— 触发扫描(单个或批量)destructive— queue_purge、tags_delete_globally、bulk_delete_targets、bulk_blocklist_targets(还要求调用本身带有confirm=True)
立即复制返回的令牌——它不会再显示。
Related MCP server: agentguard
2. 安装
cd yads-mcp
python -m venv .venv
.venv/bin/pip install -e .测试
.venv/bin/pip install -e ".[test]"
.venv/bin/pytest tests/ -qtests/conftest.py 在进程内运行 YADS(Starlette TestClient),使用与 yads 仓库自身测试相同的测试 Postgres/Redis 栈(该仓库中的 docker-compose.test.yml,端口 5433/6380)——如果这些测试未通过,请先启动该栈。
3. 配置客户端
服务器所需的环境变量:
YADS_URL— 例如https://yads.example.comYADS_API_KEY— 步骤 1 中的令牌
Claude Code
claude mcp add yads \
--env YADS_URL=https://yads.example.com \
--env YADS_API_KEY=<token> \
-- /path/to/yads-mcp/.venv/bin/python -m yads_mcp.server或添加到 .mcp.json:
{
"mcpServers": {
"yads": {
"command": "/path/to/yads-mcp/.venv/bin/python",
"args": ["-m", "yads_mcp.server"],
"env": {
"YADS_URL": "https://yads.example.com",
"YADS_API_KEY": "<token>"
}
}
}
}工具
队列与扫描控制
queue_status()queue_list_rate_limited_modules()queue_pause()/queue_resume()— 全舰队范围,不按租户隔离queue_cancel_task(task_id)queue_purge(confirm)— 破坏性操作,租户范围,60 秒撤销窗口queue_undo_purge(undo_batch)
标签与组织
tags_list()tags_add_to_target(target_id, tag)/tags_remove_from_target(target_id, tag)tags_bulk_assign(target_ids, tags, action="add"|"remove"|"replace")tags_bulk_add_by_ids(target_ids, tag)tags_delete_globally(tag_name, confirm)— 破坏性操作,不可撤销
扫描执行
scan_trigger(target_url, profile="standard")scan_trigger_by_target_id(target_id, scan_types, scan_priority=None)scan_bulk_preview_count(only_roots=False, online_only=False, scanned_before=None)scan_bulk_by_criteria(scan_types, only_roots=False, online_only=False, scanned_before=None)scan_bulk_selected(target_ids, scan_types)scan_get_findings()
目标与资产管理(第 2 波)
list_targets(tag=None, online=None, scan_status=None, domain_search=None, archived=False, last_scanned_before=None, page=1, limit=20)get_target(target_id)add_target(domain)bulk_delete_targets(target_ids, confirm)— 破坏性操作,60 秒撤销窗口undo_bulk_delete_targets(undo_batch)bulk_archive_targets(target_ids)/archive_dead_targets()/restore_target(target_id)bulk_blocklist_targets(target_ids, confirm)— 破坏性操作,不可撤销get_target_changes(target_id, limit=30)get_scan_status(target_id)get_network_context(target_id)
第 3–10 波(报告与导出、发现与合规、OSINT/发现/情报、集成/Webhooks/通知)分别跟踪,每个都有各自的设计规范。
变更日志
参见 CHANGELOG.md。
许可证
MIT — 参见 LICENSE。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables LLM-powered tools to manage Databricks permissions, credentials, and Git credentials via the MCP protocol.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables scanning of AI agent code for security vulnerabilities such as prompt injection, tool abuse, and data exfiltration, directly from MCP-compatible clients like Claude Code.1LGPL 3.0
- FlicenseNot gradedqualityCmaintenanceEnables LLM-powered agents to securely communicate with and orchestrate downstream microservices via FastAPI endpoints exposed as MCP tools.
- AlicenseNot gradedqualityBmaintenanceProvides a secure MCP gateway for AI agents to access APIs without exposing raw credentials, with scoped access, audit logging, and OAuth support.MIT
Related MCP Connectors
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
The bridge from K2 agents through Wrangler to your master AI - safe, approval-gated Cloudflare ops.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MrMarco74/yads-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server