playbook
Playbook
流程以 JSON 形式存储。按意图搜索它们,浏览标题,一次加载一个 do。
Playbook 是一个小型 CLI 和 MCP 服务器,让智能体(或你)可以编写、查找和遵循操作指南,而无需将整个 playbook 加载到上下文中。CLI 动词保持拆分。MCP 将相关动词压缩为更少的工具。一切都是 JSON。
Python 3.10+,运行时仅使用标准库。
安装
pip install -e .
playbook searchPyPI 尚未发布。
Related MCP server: servicenow-platform-mcp
文件存放位置
每个流程对应一个 JSON 文件,位于平台数据目录中:
操作系统 | 目录 |
Linux |
|
macOS |
|
Windows |
|
遵循 XDG_DATA_HOME / APPDATA / LOCALAPPDATA。命令接受流程 id,而不是路径。
结构
{
"id": "follow-playbook",
"title": "Follow a playbook procedure",
"description": "When to pick this file. Can be verbose.",
"tags": ["playbook", "follow"],
"steps": [
{
"id": "a1b2c3…",
"title": "Search by intent",
"do": "Call playbook_search with a sentence for the job."
}
]
}title — 搜索卡片上的简短名称
description — 何时选择此流程
steps — 串行。标题唯一。步骤 id 随机。
do是实际工作。
CLI
每个命令都会输出 JSON(包括错误)。
playbook create demo --title "Demo" --description "when to pick this" --tags demo
playbook add-step demo --title "First" --do "Do the first thing."
playbook add-step demo --title "Middle" --do "Do the middle." --after "First"
playbook edit demo --title "Better title"
playbook search "I want to follow a procedure"
playbook load demo
playbook load demo --full
playbook start demo --title "First"
playbook validate demo
playbook mcpsearch 采用 BM25 加上字符 n-gram。命中结果仅包含 id、title、description(默认 8 条,上限 50 条)。弱匹配会被丢弃。
load 仅包含标题。--full 包含每个 do。start 是一个 do 加上 before / after 标题。
MCP (Grok)
grok mcp add --scope user playbook -- playbook mcp如果生成的进程没有你的 shell PATH,请使用 playbook 的绝对路径。然后使用 /mcps 和 r,或新开会话。
工具 | 作用 |
| 意图搜索 |
| 加载标题、 |
| 新建流程 |
| Title / description / tags |
|
|
| 校验 |
测试
pip install -e .
python -m pytest tests/ -q许可证
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseAqualityNot gradedmaintenanceEnables AI agents to execute server-side JavaScript and perform CRUD operations directly on ServiceNow instances with context bloat reduction features for efficient token usage.31
- AlicenseAqualityAmaintenanceEnables AI agents to interact with ServiceNow through MCP, providing schema inspection, record CRUD, attachments, audit, Flow Designer, and platform investigations with policy-guarded access.142MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, share, discover, and execute reusable multi-step workflow templates.MIT
- AlicenseAqualityAmaintenanceEnables AI agents to execute multi-step Standard Operating Procedures step by step, with enforcement of completion at each step, making LLM behavior predictable and auditable.53Apache 2.0
Related MCP Connectors
Build and run visual creative-production workflows from your AI agent.
Debug, build, and manage Power Automate cloud flows with AI agents
JSON/YAML, regex, diff, JWT, SQL dialects — the keyless millisecond ops an agent needs mid-task.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/benteigland11/Playbook'
If you have feedback or need assistance with the MCP directory API, please join our Discord server