Stable Baseline

io.stablebaseline由 stablebaseline.io 發布官方發布者v1.0.4更新於 Nov 4, 2026

End-to-end agent-managed company brain. Docs, diagrams, plans, databases, agents, Knowledge Graph.

已驗證Streamable HTTP可網頁執行資料庫效率與工作流知識與記憶

概覽

AI 產生的概覽

Stable Baseline 的遠端 MCP 伺服器,讓助理在團隊工作區中建立與編輯文件、圖表、白板、資料庫、計畫與代理。

可以做什麼
  • 管理組織與結構:列出組織、查看專案階層、建立工作區與專案、邀請成員、設定團隊與權限
  • 撰寫與編輯文件及資料夾,插入圖表、白板與圖片,並匯出文件
  • 建立含檢視、表單與儀表板的資料庫,查詢資料列,上傳 CSV/JSON/TSV 資料產生圖表
  • 規劃工作:建立計畫、階段與任務,預覽相依性串接,追蹤改善項目與缺陷
  • 執行組織自有的代理:列出代理、委派工作、追蹤執行並核准其提出的動作
  • 檢索知識圖譜,並調整組織設定、計費與註冊流程
適用情境
適合希望助理在共享的公司工作區而非本機檔案中作業的情況:起草與維護文件、圖表與儀表板,規劃專案,或從任何 MCP 用戶端把工作委派給組織自有的代理。
執行需求
遠端 Streamable HTTP 端點,不需本機套件。必須透過 Authorization 標頭驗證:可使用含動態用戶端註冊的 OAuth 2.1 流程,或在組織開發者設定中建立的 sta_ 前綴 Bearer API 金鑰。需要 Stable Baseline 帳號與工作區;免費額度之外涉及付費方案與點數。
安裝前請注意
金鑰可存取工作區內容,應限定於某個工作區、專案或資料夾,而非整個組織。許多工具會寫入、邀請成員、變更權限或刪除資料,計費工具還能變更訂閱或購買點數包;涉及花費的操作採先預覽後套用並需確認權杖的流程。內容儲存在第三方雲端服務,AI 執行使用組織自己的 AI 供應商帳號。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Stable Baseline,將其新增到工作區。
  2. 連接 Authorization token 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.stablebaseline%2Fsb/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "stable-baseline": {
      "type": "http",
      "url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

[Stable Baseline]

Stable Baseline MCP Server

The simplest, most complete, end-to-end agent-managed company brain.

Website · Sign up free · Docs · Tool catalogue · llms.txt

[MCP Registry] [Smithery] [Tools] [npm CLI] [npm SDK] [PyPI]


How to use Stable Baseline

Pick the surface that matches how you work. Every option talks to the same handlers, the same auth and the same data:

SurfaceWhat it's forInstall
MCP serverAI agents (Claude Code, Cursor, Windsurf, ChatGPT, Gemini, Smithery, …). Native protocol with prompts and resources.Endpoint: api.stablebaseline.io/functions/v1/cloud-serve/mcp. See Quick start below.
REST APIAny HTTP client, Postman, OpenAPI codegen, Zapier-style integrators. Tool-RPC + idiomatic resource routes.Live spec: /api/v1/openapi.json · Interactive docs: /api/v1/docs
TypeScript SDKNode, browsers, Deno, Bun. Typed client.tools.<toolName>(...) surface.npm i @stablebaseline/sdk, see packages/sdk-typescript
CLI (sb)Shells, scripts, CI/CD. sb tool call <name> --json '{...}'.npm i -g @stablebaseline/cli, see packages/cli
Python SDKPython apps, data work. Sync + async clients.pip install stablebaseline, see packages/sdk-python

222 tools across 20 categories. Same brain, same Knowledge Graph, same RBAC on every surface.


One workspace where humans and any MCP-compatible AI agent (Claude Code, Cursor, Windsurf, VS Code, Warp, OpenCode, Antigravity, OpenAI Codex, ChatGPT Developer Mode, Gemini CLI/Extensions and more) co-author living documents (Markdown-native with a rich superset on top), 40+ visual diagrams (Mermaid, BPMN 2.0, D2, PlantUML, GraphViz, cloud architecture, sequence, state, ERD, Gantt, freehand sketches), databases with views, forms and live dashboards, plans, timelines, tasks, improvements, the organisation's own agents, and a self-learning Knowledge Graph that IS the company brain.

Lean, fast, secure and affordable: flexible enough for one person organising a personal mind, through to small businesses, growing businesses and enterprise.

222 MCP tools across 20 categories let an agent drive end-to-end: sign-up → billing → org/workspace/project → members → teams → permissions → brain scope → docs → diagrams → whiteboards → plans → databases → agents, all without a human touching the UI.

Endpoint

https://api.stablebaseline.io/functions/v1/cloud-serve/mcp

Transport: Streamable HTTP (with SSE fallback) Auth: OAuth 2.1 with Dynamic Client Registration, or Bearer API key (sta_*) Discovery manifest: https://stablebaseline.io/.well-known/mcp.json

Quick start

Create an API key (skip OAuth)

  1. Sign up free, no credit card
  2. Open Organisation settings, Connected apps, Developers, then the API keys tab, and press Create Key. Choose what it may reach; databases start unticked, so tick them if your agent should use databases
  3. Copy the sta_... key

(Or skip this: every client below also supports interactive OAuth on first call.)

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "stable-baseline": {      "url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",      "headers": {        "Authorization": "Bearer sta_YOUR_KEY"      }    }  }}

Or use the Claude Desktop OAuth flow: set just url and Claude will prompt you to authorise on first call.

Claude Code

bash
claude mcp add --transport http stable-baseline \  https://api.stablebaseline.io/functions/v1/cloud-serve/mcp \  --header "Authorization: Bearer sta_YOUR_KEY"

Or via OAuth:

bash
claude mcp add --transport http stable-baseline \  https://api.stablebaseline.io/functions/v1/cloud-serve/mcp

For skills that teach Claude Code the workflows (documents, diagrams, whiteboards, databases, dashboards and agents), install the Stable Baseline plugin for Claude Code.

Cursor

~/.cursor/mcp.json:

json
{  "mcpServers": {    "stable-baseline": {      "url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",      "headers": { "Authorization": "Bearer sta_YOUR_KEY" }    }  }}

Windsurf

~/.codeium/windsurf/mcp_config.json:

json
{  "mcpServers": {    "stable-baseline": {      "serverUrl": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",      "headers": { "Authorization": "Bearer sta_YOUR_KEY" }    }  }}

VS Code (Copilot Chat)

.vscode/mcp.json (workspace) or user settings:

json
{  "servers": {    "stable-baseline": {      "type": "http",      "url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",      "headers": { "Authorization": "Bearer ${input:sta_key}" }    }  }}

Other clients

Recipes for Warp, OpenCode, Antigravity, OpenAI Codex, ChatGPT Developer Mode, Gemini CLI/Extensions, and a generic recipe are at stablebaseline.io/docs/mcp/setup.

What you get

CategorySample toolsDocs
navigationlistOrganisations, getProjectHierarchy, searchTools→
folderscreateFolder, listFolders, setPlanItemParent→
documentscreateDocument, editDocument, exportDocument→
diagramsinsertDiagramInDocument, listDiagramTypes, getCdmdLanguageGuide→
whiteboardscreateWhiteboard, addWhiteboardElements, designDeckInWhiteboard→
imagescreateImageUploadSession, insertImageInDocument→
datacreateVegaDataUploadSession (CSV/JSON/TSV → Vega charts)→
improvementscreateImprovement, searchImprovements, addImprovementEvidence→
planscreatePlan, createPlanPhase, previewTaskDependencyCascade→
databasescreateDatabase, queryDatabaseRows, saveDatabaseDashboard→
agentslistAgents, delegateToAgent, approveAgentAction→
knowledge_graphkg_search, kg_get_entity, kg_related_documents→
organizationcreateOrganisation, createWorkspace, createProject→
membersinviteMember, updateMemberRole, setMemberActive→
teamscreateTeam, grantTeamWorkspaceAccess→
permissionsupsertResourcePermission, setResourcePermissionOverride→
billingpreviewSubscriptionChange, applySubscriptionChange, purchaseCreditPackage→
kg_adminsetKgWorkspaceScope, triggerKgRebuild, previewKgRebuild→
settingsgetOrgSettings, updateOrgFeatureFlags, createBrandKit→
signupstartSignup, pollSignupStatus→

Full live catalogue: stablebaseline.io/docs/mcp/tools

Highlights

  • End-to-end agent-managed: agents drive sign-up → billing → org/workspace/project lifecycle → members → teams → permissions → Knowledge Graph scope. No human touching the UI.
  • Living documents: AI-native rich-text editor (CDMD = Markdown + inline diagrams, data tables, media, version history, real-time multi-author edits), with PDF and Word export.
  • Visual diagram creation & editing: 40+ types, AI-generated, diagram-as-code, or freehand.
  • Databases: tables of typed fields with views, row rules, forms and live dashboards. Import CSV or Excel, and get counts, totals and groups in one call.
  • Agents: the organisation's own AI workers, each with a mandate, scoped access and approvals. Ask one or delegate a job from any MCP client, follow the run, decide its proposals, and undo a whole job.
  • Plans, timelines, tasks, improvements & bugs: Day/Week/Month/Quarter/Year zoom Gantt, drag-to-reschedule, dependency cascades.
  • Self-learning Knowledge Graph (Enterprise): auto-built from every doc, plan, improvement and database record; read by every connected agent. Stops hallucinations around gaps. Run one brain workspace-wide, one per department, or one per project, with RBAC end to end.
  • Compliance Readiness (Enterprise): scans against OWASP ASVS, NIST SSDF, CIS Controls, ISO 27001, SOC 2, TISAX. Readiness only: not legal advice, not an attestation.
  • Bring your own agent, no lock-in: any MCP-compatible client.
  • Credit-cost preview ritual for every spending operation: previewX → confirm token → applyX.

Auth

MethodWhen to use
OAuth 2.1 + Dynamic Client RegistrationDefault for desktop apps and IDE extensions. Smithery handles it automatically.
Bearer API key (sta_...)CI/CD, headless agents, server-to-server. Create one under Organisation settings, Connected apps, Developers (app.stablebaseline.io/settings/developers). Scope it to a workspace, project or folder, or let it reach the whole organisation.

OAuth endpoints:

  • authorize: https://api.stablebaseline.io/functions/v1/cloud-serve/oauth/authorize
  • token: https://api.stablebaseline.io/functions/v1/cloud-serve/oauth/token
  • register (DCR): https://api.stablebaseline.io/functions/v1/cloud-serve/oauth/register
  • Scopes: openid, profile, email, phone. These identify the signed-in user and do NOT decide what an agent may do: authorisation comes from the read/write/delete permissions per content type and the organisation capability toggles chosen on the consent screen.
  • Authoritative metadata (always prefer this over the list above): https://api.stablebaseline.io/functions/v1/cloud-serve/.well-known/oauth-authorization-server

Discovery

Pricing

  • Free: A$0, no credit card. AI runs through your organisation's own AI provider account.
  • Plus: A$39 a month (excl. GST), with 300 credits a month.
  • Pro: A$79 per user a month (excl. GST), with 500 credits per user a month.
  • Enterprise: custom. Adds the Knowledge Graph, Compliance Readiness and audit logs. Contact.

Every limit, plan by plan: stablebaseline.io/pricing.

Status

  • 🟢 MCP Registry: io.stablebaseline/sb, active, isLatest. Listed.
  • 🟢 Smithery: published with configSchema (Quick Setup). The live server lists 222 tools, 11 prompts and 8 resources.
  • 🟢 .well-known/mcp.json: live, schema 2025-06-18.
  • 🟢 Endpoint: api.stablebaseline.io/functions/v1/cloud-serve/mcp accepts POST with mcp-protocol-version: 2025-06-18.

Issues & support

License

This repository (README, llms-install.md, brand assets, and any documentation) is licensed under the MIT License, see LICENSE. You can copy, fork, and adapt these docs freely.

The Stable Baseline product itself (the SaaS application, the MCP server implementation and the company brain Knowledge Graph) is proprietary, closed-source and provided as a service at https://stablebaseline.io under the Stable Baseline Terms of Service.


Built by Orixian Solutions Pty Ltd, Sydney, Australia.

來源:README.md,提交 b5da530

工具

0
SourceWeft 尚未讀取此伺服器的工具。

版本歷史

2
  1. v1.0.4最新Oct 14, 2026
  2. v1.0.3Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分