Ticket MCP Server
Enables AI agents to manage a file-backed ticketing system directly within a local repository using a structured state machine and directory hierarchy. It enforces strict markdown schemas and provides specialized tools for claiming tasks, appending work logs, and validating ticket metadata.
README
Ticket MCP Server
Local MCP server for the repo ticket system (file-backed).
Features
- List/get/update/move/validate tickets in
tickets/ - Create new tickets with strict frontmatter validation
- Agent helpers:
tickets_next_id,tickets_claim,tickets_append_worklog,tickets_reconcile - Strict schema enforcement (rejects invalid writes)
- HTTP MCP endpoint plus optional stdio proxy
Directory Structure & State Machine
The MCP server expects a tickets/ directory in the root of your project (configured via TICKET_ROOT), containing the following subfolders that directly map to the ticket's status field. The server will strictly enforce that tickets reside in the correct folder for their status:
tickets/pending/→status: pending(Ready to be picked up)tickets/in_progress/→status: in_progressorstatus: blocked(Claimed and being worked)tickets/awaiting_human_test/→status: awaiting_human_test(AI work complete; needs human testing)tickets/done/→status: done(Human has verified and accepted)tickets/archive/→status: archived(Obsolete or old tickets)
Strict Markdown Validation
To prevent AIs from deleting context or inventing their own ticket formats, the MCP server enforces that all tickets contain specific markdown headers in their body. These headers will be automatically injected when creating a ticket via tickets_create.
Required body headers:
## Overview## Approach (medium/high-level)## Tasks / Todos## Requirements (AI implementation)## Human Testing Steps## Key Files / Areas (notes)## Questions## Blockers## Implementation Notes
Usage
Build:
npm install
npm run build
Start HTTP server:
npm run start
Auto-rebuild on changes (dev watch):
npm run dev
Run integration tests:
npm run test
Start stdio proxy (for MCP clients expecting stdio):
npm run stdio
Auto-restart stdio proxy on changes:
npm run stdio:dev
Note: build output lands under dist/ticket-mcp/src/ because the build
includes shared schema sources.
Configuration
TICKET_ROOT(default: repo root inferred from cwd)TICKET_MCP_PORT(default: 3334)TICKET_MCP_PATH(default: /mcp)TICKET_STRICT(default: true)
tickets_stats response
The tickets_stats tool returns aggregate counts plus ticket numbering metadata:
{
"status": {
"pending": 12,
"in_progress": 3,
"done": 25
},
"area": {
"tooling": 10,
"combat": 8
},
"epic": {
"none": 15,
"qa": 4
},
"highest_ticket_number": 42,
"next_ticket_number": 43
}
highest_ticket_number: highest numeric suffix parsed from existing ticket IDs (or0if none are numeric).next_ticket_number: convenience value equal tohighest_ticket_number + 1.
Agent helper tools
-
tickets_next_id- Returns
highest_ticket_number,next_ticket_number, andsuggested_id. - Optional args:
prefix(defaultT),separator(default-),padding(default3).
- Returns
-
tickets_claim- Claims a
pendingticket, moves it toin_progress, sets claim metadata, and appends awork_logentry. - Requires
actor; acceptsidorpath.
- Claims a
-
tickets_append_worklog- Appends a validated
work_logentry and updatesupdated_at. - Requires
entry; acceptsidorpath.
- Appends a validated
-
tickets_reconcile- Audits ticket invariants and optionally applies safe fixes.
- Optional
apply_fixes: truewill fix common metadata/date issues and folder/status mismatches when possible.
Recommended agent workflow
Use this sequence for normal implementation flow:
// 1) Allocate a canonical new id
const next = tickets_next_id({ prefix: "T", separator: "-", padding: 3 })
// 2) Create the ticket with suggested id
tickets_create({
id: next.suggested_id,
title: "Example ticket",
area: "tools",
epic: "none",
intent: "Why this work matters",
requirements: ["Requirement A"],
human_testing_steps: ["Do X"],
constraints: ["Constraint Y"],
key_files: ["tools/ticket-mcp/src/server.ts"],
status: "pending"
})
// 3) Claim when work starts
tickets_claim({
id: next.suggested_id,
actor: "worker-ai:example",
summary: "Starting implementation"
})
// 4) Add progress notes during execution
tickets_append_worklog({
id: next.suggested_id,
entry: {
actor: "worker-ai:example",
kind: "change",
summary: "Implemented the core logic"
}
})
// 5) Validate and reconcile before handoff
tickets_validate({ id: next.suggested_id })
tickets_reconcile({ id: next.suggested_id }) // preview only
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。