Tama MCP Server

AI-Powered Task Manager CLI with MCP Server

Local serverstdioPython

What is the Tama MCP server?

Tama MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. AI-Powered Task Manager CLI with MCP Server.

What you get

Tama 是一个命令行界面 (CLI) 工具,专为任务管理而设计,并通过 AI 能力增强,用于任务生成和分解。它利用 AI(特别配置为通过 OpenAI 兼容 API 使用 DeepSeek 模型)来解析产品需求文档 (PRD) 并将复杂任务分解为可管理的子任务。 ## 特性 * 标准任务管理: 添加、列出、显示详情、更新状态以及移除任务和子任务,支持依赖关系追踪。 * 数据持久化: 使用 SQLite 数据库存储任务数据,确保数据操作的稳定性和可靠性。 * 依赖关系管理: 添加、删除和追踪任务依赖关系,自动检测循环依赖。 * AI 驱动的 PRD 解析: (tama prd <文件路径>) 从 .txt.prd 文件自动生成结构化的任务列表。 * AI 驱动的任务分解: (tama expand <任务ID>) 使用 AI 将高层级任务分解为详细的子任务。 * 依赖检查: (tama deps) 检测和可视化任务中的循环依赖。 * 报告生成: (tama report [markdown|mermaid]) 生成 Markdown 表格格式或 Mermaid 依赖关系图的任务报告。 * 代码桩生成: (tama gen-file <任务ID>) 基于任务详情创建占位符代码文件。 * 下一任务建议:

Configuration and credentials

You will need 2 environment variables: DEEPSEEK_API_KEY, DEEPSEEK_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Choosing this one

This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. It is maintained by Gitreceiver; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Tama's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the tama mcp server does with a few real requests.

How to install the Tama MCP server

客户端配置示例:

```json
{
  "mcpServers": {
    "TAMA-MCP-Server": {
        "command": "uv",
        "args": [
            "--directory",
            "/path/to/your/TAMA_MCP",
            "run",
            "python",
            "-m",
            "src.mcp_server"
        ],
        "disabled": false,
        "transportType": "stdio",
        "timeout": 60
    },
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
DEEPSEEK_API_KEYCredential the server authenticates with.Yes
DEEPSEEK_BASE_URLEndpoint or connection string the server talks to.Yes

Frequently asked questions

Tama requires Python 3.12 and uses a virtual environment. It depends on the `tama-cli` package, SQLite for storage, and an OpenAI-compatible API key (DeepSeek models are configured by default).