trac-mcp-server
Enables AI agents to manage Trac projects with full CRUD operations on tickets, wiki pages, and milestones via the Model Context Protocol.
README
<p align="center"> <img src="img/trac_mcp_server_banner_dark_1280.png" alt="trac-mcp-server banner" /> </p>
trac-mcp-server
Standalone MCP server that gives AI agents full access to Trac project management -- tickets, wiki, milestones, and search -- via the Model Context Protocol.
Quick Start
pip install .
Set your Trac connection:
export TRAC_URL="https://trac.example.com"
export TRAC_USERNAME="your-username"
export TRAC_PASSWORD="your-password"
Run the server:
trac-mcp-server
Configuration
Configuration via environment variables, .env file, or YAML config file (.trac_mcp/config.yaml):
| Variable | Required | Default | Description |
|---|---|---|---|
TRAC_URL |
Yes | -- | Trac instance URL |
TRAC_USERNAME |
Yes | -- | Trac username |
TRAC_PASSWORD |
Yes | -- | Trac password |
TRAC_INSECURE |
No | false |
Skip SSL verification (development only) |
TRAC_DEBUG |
No | false |
Enable debug logging |
TRAC_MAX_PARALLEL_REQUESTS |
No | 5 |
Max parallel XML-RPC requests |
TRAC_MAX_BATCH_SIZE |
No | 500 |
Max items per batch operation (1-10000) |
For YAML config file format and advanced options, see Configuration Reference.
MCP Client Integration
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"trac": {
"command": "trac-mcp-server",
"env": {
"TRAC_URL": "https://trac.example.com",
"TRAC_USERNAME": "your-username",
"TRAC_PASSWORD": "your-password"
}
}
}
}
Claude Code
claude mcp add trac -e TRAC_URL=https://trac.example.com \
-e TRAC_USERNAME=your-username \
-e TRAC_PASSWORD=your-password \
-- trac-mcp-server
Other MCP Clients
Any MCP client that supports stdio transport can launch trac-mcp-server as a subprocess. Pass Trac credentials via environment variables.
Available Tools (27)
Tickets (11)
| Tool | Description |
|---|---|
ticket_search |
Search tickets with Trac query language |
ticket_get |
Get ticket details by ID |
ticket_create |
Create new tickets |
ticket_update |
Update existing tickets |
ticket_delete |
Delete tickets |
ticket_changelog |
Get ticket change history |
ticket_fields |
List available ticket fields |
ticket_actions |
Get available ticket actions |
ticket_batch_create |
Create multiple tickets in one batch |
ticket_batch_delete |
Delete multiple tickets in one batch |
ticket_batch_update |
Update multiple tickets in one batch |
Wiki (6)
| Tool | Description |
|---|---|
wiki_get |
Get wiki page content (with Markdown conversion) |
wiki_search |
Search wiki pages |
wiki_create |
Create new wiki pages |
wiki_update |
Update existing wiki pages |
wiki_delete |
Delete wiki pages |
wiki_recent_changes |
List recent wiki changes |
Wiki Files (3)
| Tool | Description |
|---|---|
wiki_file_push |
Push local file to wiki (auto format conversion) |
wiki_file_pull |
Pull wiki page to local file |
wiki_file_detect_format |
Detect content format (Markdown/TracWiki) |
Milestones (5)
| Tool | Description |
|---|---|
milestone_list |
List all milestones |
milestone_get |
Get milestone details |
milestone_create |
Create new milestones |
milestone_update |
Update existing milestones |
milestone_delete |
Delete milestones |
System (2)
| Tool | Description |
|---|---|
ping |
Test connectivity and return API version |
get_server_time |
Get Trac server time |
Development
pip install -e ".[dev]"
pytest tests/ -v
Project Structure
src/trac_mcp_server/
config.py # Environment variable configuration
core/ # Trac XML-RPC client, async utilities
mcp/ # MCP server, tools, resources
converters/ # Markdown <-> TracWiki conversion
detection/ # Content format detection
Documentation
See docs/reference/overview.md for detailed tool reference, configuration, and troubleshooting.
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。