Sponsored by Deepsite.site

Tag

#management

576 results found

Testdino Mcp

TestDino MCP is a Model Context Protocol server that lets AI agents work directly with your Playwright test data, without leaving your editor or opening a browser. Once connected, your AI assistant can browse TestDino runs, inspect failing tests, and manage manual cases using plain language. Ask it to “show the last 5 failed runs in production,” “debug the checkout flow test,” or “list all critical manual test cases in project X,” and it will call the right tools behind the scenes. The server exposes 12 focused tools for CI runs, debugging, and manual test management. You can: Check account health and validate your PAT Filter runs by branch, commit, author, time window, or environment Drill into a single test case, including errors, logs, steps, screenshots, and traces Run debug_testcase to aggregate historical failures, classify patterns, and get AI‑ready prompts for root‑cause analysis and flakiness Create, update, and organize manual test cases and suites (status, severity, tags, layers, behaviors) TestDino MCP is MCP‑compatible and works with clients like Cursor and Claude Desktop. Configure it via mcp.json using either npx testdino-mcp (no install) or a global install (npm install -g testdino-mcp), and provide a TESTDINO_PAT from your TestDino account. Typical use cases include: speeding up Playwright failure triage from within your IDE, giving AI agents structured access to real test history, and keeping manual test management in sync with how your team actually debugs CI.

Mcp Server For Bitrix24

# mcp-bitrix24 MCP server for Bitrix24 Tasks, Workgroups, and Users. Implements MCP/JSON-RPC over STDIO. ## Features - Tasks: create, update, close, reopen, list - Workgroups: create, list - Users: list, current user, available fields - Task fields: available fields + validation for `create_task.fields` ## Requirements - Node.js >= 18 - Bitrix24 webhook URL ## Install / Build ```bash npm install npm run build ``` Run via npm: ```bash npx mcp-bitrix24 ``` ## Configuration Set the Bitrix24 webhook URL via environment variable: ``` BITRIX24_WEBHOOK_URL=https://<your-domain>/rest/<user_id>/<webhook>/ ``` Example Codex MCP config: ```toml [mcp_servers.bitrix24] command = "npx" args = ["-y", "mcp-bitrix24"] [mcp_servers.bitrix24.env] BITRIX24_WEBHOOK_URL = "https://<your-domain>/rest/<user_id>/<webhook>/" ``` ## Tools ### Tasks - `create_task` - Input: `title` (string, required), `description?` (string), `responsible_id?` (number), `group_id?` (number), `fields?` (object) - Output: `{ task_id: number }` - Note: if `fields` is provided, keys are validated against `get_task_fields`. - `update_task` - Input: `task_id` (number, required) + at least one of: `title?`, `description?`, `responsible_id?`, `group_id?` - Output: `{ task_id: number }` - `close_task` - Input: `task_id` (number, required) - Output: `{ task_id: number }` - `reopen_task` - Input: `task_id` (number, required) - Output: `{ task_id: number }` - `list_tasks` - Input: `responsible_id?` (number), `group_id?` (number), `start?` (number), `limit?` (number) - Output: `{ tasks: [{ id, title, status }] }` - `get_task_fields` - Input: `{}` - Output: `{ fields: { [field: string]: object } }` - `list_task_history` - Input: `task_id` (number, required), `filter?` (object), `order?` (object) - Output: `{ list: [ { id, createdDate, field, value, user } ] }` ### Workgroups - `create_group` - Input: `name` (string, required), `description?` (string) - Output: `{ group_id: number }` - `list_groups` - Input: `limit?` (number) - Output: `{ groups: [{ id, name }] }` ### Users - `list_users` - Input: - `filter?` (object) - `sort?` (string) - `order?` ("ASC" | "DESC") - `admin_mode?` (boolean) - `start?` (number) - `limit?` (number) - Output: `{ users: [{ id, name, last_name, email?, active }] }` - Note: `filter` supports Bitrix24 `user.get` filters (including prefixes like `>=`, `%`, `@`, etc.). `start` controls paging (Bitrix returns 50 records per page); `limit` is a local slice after the API response. - `get_user_fields` - Input: `{}` - Output: `{ fields: { [field: string]: string } }` - `get_current_user` - Input: `{}` - Output: `{ user: { id, name, last_name, email?, active } }` ## Architecture Clean architecture layers: - `mcp/` — protocol, transport, server - `adapters/` — MCP tools mapping to domain - `domain/` — entities, services, ports - `infrastructure/` — Bitrix24 REST client ## Development Notes - Input validation uses `zod`. - Transport: STDIO only. - Build: `tsc` (`npm run build`). ## Contributing See `CONTRIBUTING.md` for guidelines.

缔零科技mcp

缔零法则MCP是专为审核安全领域打造的AI智能防御中枢,致力于通过Agentic AI 技术减少人力成本,高效高精度为用户提供分钟级接入的内容风控解决方案,破解安全威胁,提供从风险感知到主动拦截策略执行的全链路闭环与一体化解决方案。 核心特点 使用简单接入便捷:无需部署本地服务,通过简单配置即可使用; 运维成本较低:用户无需关心服务器维护、资源扩容等底层运维问题。 协议兼容:多模态支持,适配不同客户不同业务不同内容审核场景的技术接入需求。 易集成:标准 MCP 协议,主流 AI/Agent/workflow 皆可用 三、核心功能矩阵 1、全风险域覆盖 一次性识别所有内容风险类型,无需多系统切换。最高支持30种风险域,支持 350+细分标签,一次调用完成全域扫描,无需重复对接不同审核接口 2、极速响应能力 将审核效率提升至人工的 50倍,平均审核时间20秒;规则变动时 30分钟完成策略调整;新风险场景 5天快速接入适配 3、智能识别引擎 通过深度语义分析应对复杂风险场景,通过上下文关联重建,解析识别变体表达和隐藏含义;同时通过动态策略优化,根据实时风险数据自动调整审核阈值,自动学习新型违规模式。 4、多模态融合审查 可统一处理文本、图像内容。通过图文混合审核既即可实现AIGC内容专项治理,拦截违规生图提示词及输出。 5、企业级风险管理工具 客户可无培训成本直接使用;同时具备策略配置中心,以自然语言定义规则为基础设置分级审核机制,精准审核