bailinghub-mcp-server
Submit and inspect governed business-system actions through a BailingHub control plane, with tools for submitting, retrieving, and waiting on governed jobs.
README
BailingHub MCP Server
Use MCP hosts to submit and inspect governed business-system actions through a self-hosted BailingHub control plane.
This package is a thin integration adapter. It does not embed BailingHub, grant business permissions, authenticate an end user, or replace the downstream business system's final authorization.
What It Exposes
| Tool | Purpose |
|---|---|
submit_governed_job |
Submit untrusted task text to one operator-configured BailingHub route |
get_governed_job |
Read the current public state of a client-owned job |
wait_for_governed_job |
Poll one job for at most 60 seconds without resubmitting it |
The route, BailingHub URL, and Client Token are process configuration. They are never MCP tool arguments and therefore cannot be selected or replaced by model output.
Security Model
MCP host / model
|
| request_id + untrusted input
v
BailingHub MCP Server
|
| fixed route + route-scoped Client Token
v
BailingHub
|
| governed dispatch
v
Business system
|
+-- resolves trusted subject and performs final authorization
The adapter intentionally does not accept:
- an acting subject or identity claim;
- a Client Token, administrator token, or business-system credential as tool input;
- an approval decision or approval evidence;
- an executor identity;
- arbitrary metadata or callback URLs;
- an arbitrary route.
Use a dedicated BailingHub Client Token restricted to the one route configured for this server process. Run separate server instances when different MCP clients need different route boundaries.
Install
Prerequisites:
- Node.js 20.15 or newer;
- a reachable BailingHub deployment;
- one BailingHub Client Token restricted to the required route.
Configure an MCP host to spawn:
{
"mcpServers": {
"bailinghub": {
"command": "npx",
"args": ["-y", "bailinghub-mcp-server"],
"env": {
"BAILINGHUB_BASE_URL": "https://hub.example.com",
"BAILINGHUB_CLIENT_TOKEN": "replace-with-a-route-scoped-client-token",
"BAILINGHUB_ROUTE": "order_assistant"
}
}
}
}
For a local BailingHub process, loopback HTTP is accepted:
BAILINGHUB_BASE_URL=http://127.0.0.1:3000
Non-loopback HTTP is rejected by default. BAILINGHUB_ALLOW_INSECURE_HTTP=true exists only
for an operator-controlled private network where TLS terminates elsewhere. Do not use it
across an untrusted network.
Correct Job Flow
- Create a stable
request_idfor one business request. - Call
submit_governed_jobwith that ID and the task text. - Preserve the returned
job_id. - Call
wait_for_governed_jobfor a short bounded wait, or callget_governed_joblater. - If submission must be retried, reuse the exact same
request_idand task meaning.
queued, running, and dispatched are non-terminal. done, error, and rejected are
terminal. A wait timeout is not a failed task and must not cause a replacement submission.
First Success and Feedback
Use the MCP integration path as the
canonical start page. The first integration is successful when an MCP host submits through
the operator-fixed route, the same job_id reaches a terminal state, BailingHub retains
its approval and audit state, and the MCP host never receives administrator or
business-system credentials.
Report a PASS, partial result, or failure through the BailingHub independent validation form and select the MCP track. Never include tokens, model keys, personal information, or production business data.
Project Boundaries
The dependency direction is one-way:
bailinghub-mcp-server -> BailingHub public Client API
BailingHub may consume ACC declarations
ACC has no dependency on either implementation
See:
Development
npm install
npm run verify
npm pack --dry-run
The integration uses the stable bailing.client-api.v1 surface only:
POST /runGET /jobs/{job_id}
No administrator, executor, approval-decision, tool-proxy, configuration, or direct business API is called.
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。