context-studio
MCP server for Context Studio, a file-based CMS for governed marketing documents and searchable collections, enabling retrieval and management of AI context via tools like scopes, document reads, and collection search.
README
Context Studio
Context Studio is a file-based context CMS for governed marketing Documents plus searchable supporting Collections. We use plain folders, Markdown, YAML frontmatter, SQLite, and Git so teams can inspect, edit, validate, and retrieve AI context without a heavy knowledge-platform stack.
The system is intentionally simple:
- Documents are OKF-style Markdown records in a normal folder tree.
- Collections are source-file buckets indexed locally for cited retrieval.
- Git provides history, diffs, restore, and backup.
- SQLite stores users, audit events, and Collection indexes.
- FastAPI serves the API, MCP endpoint, and production CMS bundle.
- Astro provides the browser UI.
- Docker/Render can host the demo as one web service.
What It Does
- Stores governed marketing context as Markdown files.
- Uses folder metadata and document frontmatter for scope, type, status, and criticality.
- Keeps curated Documents separate from searchable supporting Collections.
- Avoids semantic search over governed Documents; scoped retrieval is deterministic.
- Uses Collection search only when a surfaced Document or folder points to that Collection.
- Exposes MCP tools for scopes, types, folders, indexes, logs, document metadata, document reads, Collection search, source reads, and validation.
- Provides a browser MCP Test Tool so we can test agent-facing retrieval behavior directly.
Context Solution Guide
MARKETING_CONTEXT_GUIDE.md explains the larger marketing-team context model behind this prototype: how context should be structured, governed, retrieved, and separated from skills and outcome specs.
Try the Demo
Hosted demo:
https://context-studio-demo.onrender.com/
Demo logins:
admin / admin123
editor / editor123
viewer / viewer123
The hosted demo uses synthetic data. Edits are useful for testing but should be treated as ephemeral on the free Render service.
Run It Yourself
Local setup:
Render deployment:
Screenshots
Documents

Collections

MCP Test Tool

Demo Data
The tracked demo/ folder contains synthetic demo assets:
demo/context_repo/contains governed marketing Documents for the Context Studio demo brand.demo/sample_sources/contains synthetic transcript files for Collection seeding.demo/screenshots/contains README screenshots.
Editable runtime data is ignored by Git and lives under .local/ by default.
Reset local demo data:
uv run python run.py reset-demo
Tests
uv run pytest
cd cms && npm run build
uv run python run.py validate
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。