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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.