Strapi MCP Server
Enables AI assistants to connect to Strapi CMS for browsing, creating, editing, publishing, and managing content through natural language.
README
Strapi MCP Server
A Model Context Protocol (MCP) server that connects AI assistants to your Strapi CMS. Enables AI to browse, create, edit, publish, and manage content through natural conversation.
Features
- Full CRUD — Create, read, update, delete content entries
- Schema introspection — AI discovers your content types, fields, and relations automatically
- Publish workflow — Publish and unpublish entries directly
- Media management — Browse, upload, and update media files (alt text, captions)
- i18n support — Work with multiple locales
- Secure auth — Login with Strapi admin credentials, role-based permissions
- Single & Collection types — Handles both seamlessly
- Zero config on CMS side — Uses Strapi's built-in admin API, no plugins required
Tools
| Tool | Description |
|---|---|
login |
Authenticate with Strapi admin credentials |
get_session |
Check current user and role |
list_content_types |
Discover all content types and their structure |
describe_content_type |
Get detailed field definitions for a content type |
list_entries |
Browse entries with pagination |
get_entry |
Fetch a single entry with all fields |
create_entry |
Create new content |
update_entry |
Update existing content |
delete_entry |
Delete content |
publish_entry |
Make content live on the website |
unpublish_entry |
Revert to draft |
list_media |
Browse Media Library |
upload_media |
Upload files to Media Library |
update_media |
Update file metadata (alt text, caption, name) |
Quick Start
Install
npm install -g github:devels-ai/strapi-mcp-server
Configure
Add to your AI client's MCP configuration:
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"strapi": {
"command": "strapi-mcp-server",
"env": {
"STRAPI_URL": "https://your-strapi-instance.com"
}
}
}
}
Claude Code (~/.claude/settings.json):
{
"mcpServers": {
"strapi": {
"command": "strapi-mcp-server",
"env": {
"STRAPI_URL": "https://your-strapi-instance.com"
}
}
}
}
Cursor: Settings → MCP Servers → Add the same configuration.
Use
After restarting your AI client:
- AI will ask for your Strapi admin email and password
- Once authenticated, ask it to help with content — e.g.:
- "Show me all content types"
- "Create a new news article about our product launch"
- "Update the home page hero title"
- "List all unpublished drafts"
- "Upload this image and set the alt text"
How It Works
The MCP server connects to Strapi's admin API using your credentials. It inherits your role's permissions — if your Strapi account can't delete content, the AI can't either.
AI Client ←→ MCP Server ←→ Strapi Admin API
(local) (your server)
- MCP server runs locally on your machine
- Communicates with AI via stdio (standard MCP transport)
- Calls Strapi's admin REST API over HTTPS
- JWT token stored in memory only (per session)
Requirements
- Node.js 18+
- Strapi v5
- A Strapi admin account
Environment Variables
| Variable | Description | Default |
|---|---|---|
STRAPI_URL |
Your Strapi instance URL | http://localhost:1337 |
Security
- Credentials are sent directly to your Strapi instance — never to third parties
- JWT tokens are stored in memory only, never persisted to disk
- The MCP server respects your Strapi role permissions
- No data leaves your infrastructure
License
MIT
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.