BailingHub for Business Operations

io.github.bailinghubPublished by GitHub account bailinghubv0.8.0Updated Oct 27, 2026

Let AI agents query and operate business systems with authorization, approval and audit trails.

Overview

AI-generated overview

Local stdio adapter that lets an AI agent submit natural-language jobs to one fixed, operator-configured BailingHub route for governed business-system actions.

What you can do
  • Submit untrusted task text to one operator-configured BailingHub route as a governed job
  • Read the current public state of a job and poll it for a bounded wait without resubmitting
  • In Agent Session mode, bootstrap a turn, search and read business capabilities and reference guidance, invoke or resume governed tool calls, and mark a run complete
  • Query and operate business systems such as store, SaaS, CRM or ERP within the exposed capabilities, with approval and audit handled by BailingHub
When to use it
Use it when an organization already runs a self-hosted BailingHub deployment and wants an MCP host to issue business requests, such as stock checks, profile updates or refund requests, through a fixed route with authorization, approval and audit trails kept outside the model.
Requirements
Node.js 20.15 or newer and a reachable BailingHub deployment. Either a route-scoped Client Token in BAILINGHUB_CLIENT_TOKEN, or a one-time browser login for an approved Agent Session. BAILINGHUB_BASE_URL and BAILINGHUB_ROUTE are required; non-loopback HTTP is rejected unless BAILINGHUB_ALLOW_INSECURE_HTTP is set. Desktop-only local process.
Before you install
Requires a secret Client Token; use a dedicated token restricted to the single configured route and run separate instances for different route boundaries. Jobs can change business data such as profiles, prices or refunds, and some routes wait for human approval. The adapter is a thin integration layer and does not grant permissions; the downstream business system makes the final authorization decision. Avoid enabling insecure HTTP across untrusted networks.

Installation

In SourceWeft

  1. Open BailingHub for Business Operations in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

BailingHub MCP Server

0.8.0: larger tool inputs and knowledge on demand

Save complete page content without a small adapter limit, read only the relevant business guidance, and choose model defaults independently of service ceilings. Pair Core 0.10.0 / SDK 0.8.0 / DSH 0.8.0. Existing authorization, approval and original-operation recovery remain in force; automatic task continuation is a host responsibility.

Changes · Upgrade

简体中文 | English

Let an MCP-compatible AI agent use natural-language requests to query and operate your store, SaaS, CRM, ERP, or other business system through BailingHub.

Depending on the capabilities explicitly exposed by the business system and the routes allowed for this connection, an agent can, for example:

  • find products with fewer than 10 items in stock and prepare a restocking suggestion;
  • update an employee or customer profile;
  • submit a refund request and wait when the configured route requires human approval.

The agent does not receive administrator or business-system credentials. BailingHub keeps the route boundary, approval state, execution record, and audit trail, while the downstream business system still makes the final authorization decision.

Previously introduced in 0.5.0: shop and inventory in one conversation

A host can let a user ask: “Check tumbler stock; if available, change the corresponding shop product to 59 and list it.” This SDK adds original-target checks for different systems on one Hub, system descriptions before tool search, and business-supplied authorization names. Actions must be exposed by the business systems, product mappings confirmed, and original approvals respected.

Use Core 0.10.0 + SDK 0.8.0 and a compatible host for these extensions, within one Hub and one administrator audit domain. The host owns explicit selection and persistent scope; the standalone MCP server does not gain a multi-system selection UI.

Scenarios, changes and upgrade steps

Conversation archives introduced in 0.4.0

When an Agent Client host enables conversation archiving, a BailingHub administrator can follow the user's request, the assistant's visible replies and the resulting business actions together. For example, one conversation can compare two separately authorized stores while retaining the original execution record for each store. Use BailingHub Core 0.10.0 with a host that captures and synchronizes the conversation. The archive API minimum is Core 0.6.0.

Version 0.4.0 introduced that synchronization API. It does not capture conversations by itself. A native host such as the DSH plugin owns the account selection and conversation interface. The standalone MCP server keeps its existing tool surface.

Who should upgrade, and where to start

Your setupNext step
You use an MCP application with a fixed business routeInstall this package at 0.8.0 using the MCP setup below. Your existing Client Token and Agent Session flows remain compatible.
You use a native Agent Client, such as DSHUpgrade through that host's matching release and follow its account-selection guide. Installing this MCP command alone does not add a multi-account conversation UI.
You build an Agent Client hostInstall [email protected], use Core 0.10.0 for the complete feature set, and follow the SDK guide.

You do not need to change business API declarations for this SDK upgrade. Existing read/write, approval and invocation recovery behavior stays in place. Conversation upload retries use the same event IDs and never repeat business actions; only the deployment's authorized administrators can read the combined archive. Hidden reasoning is excluded.

This package is a thin integration adapter. It does not embed BailingHub, grant business permissions, or replace the downstream business system's final authorization. It supports both the existing operator-provisioned Client Token mode and an Agent Session mode in which a human approves one local Agent through the system browser.

What It Exposes

ToolPurpose
submit_governed_jobSubmit untrusted task text to one operator-configured BailingHub route
get_governed_jobRead the current public state of a credential-owned job
wait_for_governed_jobPoll one job for at most 60 seconds without resubmitting it

The Agent Session MCP path starts with seven small meta-tools for turn bootstrap, capability and reference-knowledge search/read, governed invocation/recovery, and visible run completion. BailingHub then returns at most 12 active business tools for the current turn; each replacement removes the previous active set instead of growing the model context indefinitely.

Short tool descriptions can include description_truncated and usage_guidance_available flags in start/search results. To read only one loaded tool's bounded guidance, call search_business_capabilities with {"tool_name":"the_exact_loaded_name","include_usage_guidance":true} after starting the turn. This is a read-only reference bound to the current run, authorization and catalog revision; it does not invoke the business tool. Preserve the returned truncation and size metadata. Older clients without detail support return a compatibility error; ordinary search remains compatible.

Host implementers should use the host-neutral Agent Client SDK guide.

The route, BailingHub URL, and credential are local process configuration, never model-supplied MCP tool arguments. An SDK host may publish a fixed set of available authorization references for per-call selection within one system; the host resolves each reference to its captured connection and retains control of connection management. See the authorization-reference guidance.

Authentication Modes

  • Agent Session: run bailinghub-mcp-server login once. The CLI uses a random loopback callback plus PKCE, opens the system browser, and stores the approved session in the platform-specific secure credential store. The MCP tools then use /agent-api/v1/* and refresh rotated tokens locally.
  • Client Token (compatible): when BAILINGHUB_CLIENT_TOKEN is present, the adapter keeps using POST /run and GET /jobs/{job_id} exactly as before.

Neither mode lets the model supply a credential, route, acting subject, or approval result. The Agent Session records the identity approved by the Hub/business authorization boundary; the downstream business system still makes the final authorization decision.

The MCP Registry server.json describes only the compatible standalone stdio/Client Token installation, so that entry still marks BAILINGHUB_CLIENT_TOKEN as required. The native DSH plugin does not consume that Registry configuration: it imports this package's /sdk subpath as an ordinary library dependency and establishes an Agent Session through the browser. Do not add a Client Token field to a DSH plugin based on the Registry form.

Security Model

text
MCP host / model    |    | request_id + untrusted input    vBailingHub MCP Server    |    | fixed route + Client Token or approved Agent Session    vBailingHub    |    | governed dispatch    vBusiness 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.

In compatible Client Token mode, use a dedicated 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;
  • either one route-scoped BailingHub Client Token or a registered public Agent client that can be approved for the required route.

For the legacy static-job mode, configure an MCP host to spawn:

json
{  "mcpServers": {    "bailinghub": {      "command": "npx",      "args": ["-y", "[email protected]"],      "env": {        "BAILINGHUB_BASE_URL": "https://hub.example.com",        "BAILINGHUB_CLIENT_TOKEN": "replace-with-a-route-scoped-client-token",        "BAILINGHUB_ROUTE": "order_assistant"      }    }  }}

Agent Session login

Authorize one registered public Agent client and one fixed route before starting the MCP host without a Client Token:

bash
npm install --global [email protected]
bailinghub-mcp-server login \  --base-url https://hub.example.com \  --client-app-id merchant-agent \  --route order-assistant
bailinghub-mcp-server statusbailinghub-mcp-server logout

The login callback binds only to a random 127.0.0.1 port and uses state plus PKCE S256. Access and refresh tokens never appear in CLI output. macOS uses Keychain. Linux and other POSIX platforms require an explicit BAILINGHUB_ALLOW_FILE_CREDENTIAL_STORE=true opt-in; that fallback rejects files that are not owned by the current user with mode 0600. Windows uses a CurrentUser DPAPI-protected file under the user's LocalAppData directory. If Windows PowerShell or DPAPI is unavailable, Agent Session fails closed and never falls back to plaintext. Compatible Client Token mode remains available on every supported platform.

For a local BailingHub process, loopback HTTP is accepted:

text
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

  1. Create a stable request_id for one business request.
  2. Call submit_governed_job with that ID and the task text.
  3. Preserve the returned job_id.
  4. Call wait_for_governed_job for a short bounded wait, or call get_governed_job later.
  5. If submission must be retried, reuse the exact same request_id and 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:

text
bailinghub-mcp-server -> BailingHub public Client API / Agent APIBailingHub may consume ACC declarationsACC has no dependency on either implementation

See:

Development

bash
npm installnpm run verifynpm pack --dry-run

Client Token mode uses the stable bailing.client-api.v1 surface:

  • POST /run
  • GET /jobs/{job_id}

Agent Session mode uses the additive Agent Auth v1 and Agent API v1 surfaces:

  • POST /agent-auth/v1/authorizations
  • POST /agent-auth/v1/token
  • GET /agent-auth/v1/session
  • POST /agent-auth/v1/revoke
  • GET /agent-api/v1/workspaces
  • GET /agent-api/v1/workspaces/{route}/bootstrap
  • POST /agent-api/v1/workspaces/{route}/turns
  • POST /agent-api/v1/workspaces/{route}/capabilities/search
  • POST /agent-api/v1/tool-invocations
  • POST /agent-api/v1/tool-invocations/{invocation_id}/resume
  • POST /agent-api/v1/runs/{run_id}/complete

The host SDK additionally uses conversation audit write APIs available from Core 0.6.0. Use Core 0.8.0 for the new cross-system mode, system descriptions and authorization names. These APIs are not exposed as MCP/model tools:

  • POST /agent-api/v1/conversation-audits
  • POST /agent-api/v1/conversation-audits/{conversation_id}/confirm
  • POST /agent-api/v1/conversation-audits/{conversation_id}/events

The bailinghub-mcp-server/sdk subpath additionally exposes a host-neutral Agent Client factory. It owns browser login, named local selectors, isolated credentials, token refresh, and Core DTO mapping. On the same Hub/client/workspace binding it replaces an older local connection only when Core reports the same trusted on_behalf_of; different business identities remain independently selectable. Core resolves the business authorization entry, so host adapters such as DSH never ask for a business URL and do not own credentials or BailingHub HTTP endpoint details.

No administrator, executor, approval-decision, tool-proxy, configuration, or direct business API is called by this adapter.

Source: README.md at commit b830afa

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the server did not start.

Version history

3
  1. v0.8.0LatestOct 22, 2026
  2. v0.7.0Sep 23, 2026
  3. v0.6.0Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts