agent-ops-mcp
agent-ops-mcp
一个演示 MCP 服务器,展示了我为团队构建的配置形态:一个直接读写我们内部系统的智能体,而不是有人手动将上下文粘贴到聊天中,外加一个轻量级质量门,在代理产出的内容到达人工审查者之前对其进行检查。
真实版本会对接我们实际的任务跟踪器、内部文档和 CI——该代码不公开。这个仓库是同一想法基于模拟数据的自包含重建,因此它可以独立运行,无需任何凭据或访问任何内部资源。
暴露的工具
工具 | 功能 |
| 从模拟跟踪器列出任务,可按状态/负责人筛选 |
| 按 id 获取单个任务 |
| 创建任务 |
| 在小型模拟内部 wiki 上进行全文搜索 |
| 按 id 获取文档的完整内容 |
| 启发式预审门——标记硬编码的机密、遗留的 |
review_check 是其中有趣的一个:与其让人类在审查时发现遗漏的 TODO 或硬编码的密码,不如让代理先在自己的输出上运行这个检查。它对应了仓库内附带的 review-checklist 文档。
Related MCP server: MCP Document & Task Server
运行
npm install
npm run build
npm start这会通过 stdio 启动一个 MCP 服务器。要从 Claude Desktop 或 Claude Code 尝试,请将其添加到你的 MCP 配置中:
{
"mcpServers": {
"agent-ops-mcp": {
"command": "node",
"args": ["/absolute/path/to/agent-ops-mcp/dist/index.js"]
}
}
}无需构建步骤的本地开发:
npm run dev数据
所有内容都驻留在内存中,启动时从 src/data/tasks.ts 和 src/data/docs.ts 初始化。create_task 会修改内存中的列表——每次运行状态都会重置,不会写入磁盘。
技术栈
TypeScript、Node.js、@modelcontextprotocol/sdk、Zod 用于输入验证。
许可证
MIT
Available Tools
6 toolscreate_taskCreate taskC
Create a new task in the tracker.
Inputs: title (required), assignee (required), tags, priority.
get_docGet docA
Fetch the full content of a doc by id (from search_docs results).
Inputs: id (required).
get_taskGet taskB
Get a single task by id.
Inputs: id (required).
list_tasksList tasksA
List tasks from the team tracker, optionally filtered by status or assignee.
Inputs: status, assignee.
review_checkPre-review quality gateA
Run heuristic checks (secrets, leftover TODOs, placeholder text, size) over generated text or a diff before it goes to a human reviewer — mirrors the team's pre-review checklist doc.
Inputs: text (required).
search_docsSearch internal docsA
Full-text search over the internal docs/wiki (style guide, runbooks, checklists). Stands in for hitting a real Confluence-style docs API.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct resource and action: tasks (list/get/create), docs (search/get), and a review check. There is no overlap or ambiguity between them. An agent can easily select the right tool for each intent.
All tool names follow a consistent snake_case verb_noun pattern (list_tasks, get_doc, review_check). The verbs are clear and the style is uniform throughout. This makes the API predictable and easy to extend.
With only 6 tools, the surface is well-scoped and focused. Each tool earns its place by covering a necessary operation without bloat. This is an ideal size for an agent helper that combines tasks, docs, and quality checks.
Task management is incomplete: you can create and list tasks but cannot update, delete, or change status, which are common operations. Docs are read-only (search/get), which is acceptable for a reference. Adding update/delete for tasks would round out the lifecycle.
Maintenance
Related MCP Connectors
Shared task layer for AI agents: tasks, handoffs and decisions that persist across tools.
Task and bug tracker for AI coding agents: 75 tools to file, triage and update work.
Public web tools for agents: product extraction, claim checks, webpage QA and ranked audits.
Task manager for AI agents. Orchestrate agents to achieve large goals in unified control plane.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.71MIT
- AlicenseBqualityDmaintenanceProvides a document database with search, retrieval, and creation tools, and a task tracker with search and status filtering, enabling AI agents to manage documents and tasks via natural language.3MIT
- FlicenseAqualityDmaintenanceTransforms internal Hermes documents (PRDs, RFCs, specs) into agent tools for relevance search, metadata, and full content retrieval, plus a skill to cross-check specs against code.8-
- FlicenseNot gradedqualityDmaintenanceExposes task management (add, list, complete tasks) and document search (RAG) as MCP tools for AI agents.-