Stable Baseline
@stablebaseline
Stable Baseline について
Stable Baseline MCP server — end-to-end agent-managed company brain. 163 tools, OAuth 2.1 + Bearer API key, remote Streamable HTTP.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"stable-baseline": {
"url": "https://api.stablebaseline.io/functions/v1/cloud-serve/mcp",
"headers": {
"Authorization": "Bearer sta_YOUR_API_KEY"
}
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Stable Baseline?
Stable Baseline is a cloud-hosted MCP server that acts as an end-to-end agent-managed company brain. It integrates with any MCP-compatible AI agent (Claude Code, Cursor, Windsurf, ChatGPT, Gemini, etc.) and offers 193 tools across 18 categories for documents, diagrams, plans, knowledge graphs, billing, and more. It is designed for individuals, teams, and enterprises who want a single workspace where humans and AI co-author living content.
How to use Stable Baseline?
Pick a surface that matches your workflow: the MCP server endpoint (https://api.stablebaseline.io/functions/v1/cloud-serve/mcp), REST API, TypeScript SDK (npm i @stablebaseline/sdk), Python SDK (pip install stablebaseline), or CLI (npm i -g @stablebaseline/cli). Quick start: sign up free at app.stablebaseline.io, generate an API key (starts with sta_), and configure your client with the endpoint and bearer token, or use OAuth 2.1 for interactive flows. Configuration examples are provided for Claude Desktop, Claude Code, Cursor, Windsurf, and VS Code.
Key features of Stable Baseline
- End-to-end agent-managed lifecycle: sign-up to billing, permissions, and brain scope.
- Living documents with AI-native rich-text editor and inline diagrams.
- 40+ visual diagram types (Mermaid, BPMN, PlantUML, Excalidraw, etc.).
- Plans, timelines, tasks, improvements with Gantt and dependency cascades.
- Self-learning Knowledge Graph auto-built from every document and plan.
- 193 MCP tools across 18 categories, all accessible from any MCP client.
Use cases of Stable Baseline
- An AI agent creates a project, invites members, and sets permissions without human UI interaction.
- Teams co-author technical specifications with inline diagrams and real-time edits.
- Project managers plan phases, assign tasks, and preview dependency cascades via an agent.
- Enterprise users run compliance readiness scans against OWASP ASVS, NIST SSDF, and others.
- A developer connects multiple AI agents (Claude Code, Cursor, Gemini) to the same workspace brain.
FAQ from Stable Baseline
What exactly is Stable Baseline?
It is a cloud-based workspace where humans and MCP-compatible AI agents co-author documents, diagrams, plans, and a self-learning Knowledge Graph – all accessible via 193 MCP tools.
How do I authenticate with the MCP server?
You can use OAuth 2.1 with Dynamic Client Registration (for desktop apps and IDE extensions) or a static Bearer API key (starts with sta_) for CI/CD, headless agents, and server-to-server integration. API keys are minted in the app settings.
What clients are supported?
Claude Desktop, Claude Code, Cursor, Windsurf, VS Code Copilot Chat, Warp, OpenCode, Antigravity, OpenAI Codex, ChatGPT Developer Mode, Gemini CLI/Extensions, and any MCP-compatible client via the generic HTTP recipe.
Is there a free tier?
Yes. The Free plan gives 100 one-off credits with no credit card required. Pro is A$79/user/month (500 credits/user/month). Enterprise plans are custom and include Knowledge Graph, compliance readiness, audit logs, and SSO.
Where is my data stored and is it secure?
Data resides in Stable Baseline’s cloud infrastructure. Access is controlled by RBAC (Role-Based Access Control) end-to-end. The service supports OAuth 2.1, bearer API keys, and project-scoped or global API keys. Enterprise plans offer audit logs and SSO.
「AI とエージェント」の他のコンテンツ
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Mcp Agent
lastmile-aiBuild effective agents using Model Context Protocol and simple workflow patterns
Model Context Protocol Server for Home Assistant
tevonsbA MCP server for Home Assistant
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
コメント