squidex-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@squidex-mcpList the content schemas in my Squidex app"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
squidex-mcp (non-official)
An MCP (Model Context Protocol) server that lets AI agents read and write Squidex CMS content directly. MCP is an open, model-agnostic protocol — any compliant client works (Claude Code, Claude Desktop, Cursor, Windsurf, custom agents on any model), not just Anthropic's. Built on Bun for fast, dependency-free startup — each agent session spawns its own server process over stdio.
What it can do
Tool | Purpose |
| List content schemas in the app |
| Get a schema's fields, including field ids and localization mode |
| Create a new content schema |
| Add a field to a schema (including nested Array/Component fields) |
| Replace a field's properties |
| Publish a schema so content can be created against it |
| Delete a schema — for discarding a failed design iteration |
| Query content items (OData-style |
| Get a single content item |
| Create a content item |
| Replace a content item's data |
| Delete a content item |
| Change workflow status (Draft/Published/Archived) |
| List/query the asset library |
| Get a single asset's metadata by id |
| Upload a new asset from a local file or a remote URL |
| List the app's configured languages, for partitioning localized fields |
| List configured Squidex profiles (no secrets) |
It can target multiple Squidex apps/instances (e.g. prod + staging) from one running server — every tool takes an optional profile parameter, switchable without restarting the server. See Profiles below.
Related MCP server: Storyblok MCP
Quick start (no coding required)
The easiest way to run it is via npx — no download, no build step, just a Node.js install (which most machines already have).
1. Get your Squidex credentials
In your Squidex app: Settings → Clients → create (or copy) a client. You need:
your Squidex URL (e.g.
https://cloud.squidex.io)your app name
the client ID (looks like
your-app-name:default)the client secret
2. Register the server with your MCP client
Claude Code:
claude mcp add \
--env SQUIDEX_URL=https://cloud.squidex.io \
--env SQUIDEX_APP=your-app-name \
--env SQUIDEX_CLIENT_ID=your-app-name:default \
--env SQUIDEX_CLIENT_SECRET=your-client-secret \
--transport stdio squidex \
--scope user \
-- npx -y @shalotts/squidex-mcp--scope user makes it available in every project, not just the current one. -y stops npx from pausing on an interactive "ok to install?" prompt, which would otherwise hang the connection on first run.
Claude Desktop: edit Claude Desktop's own config file for your OS (this is Claude Desktop's launcher config, not squidex.config.json from Profiles below — the env block here just sets environment variables for the process Claude Desktop spawns) —
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json ·
Windows: %APPDATA%\Claude\claude_desktop_config.json ·
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"squidex": {
"command": "npx",
"args": ["-y", "@shalotts/squidex-mcp"],
"env": {
"SQUIDEX_URL": "https://cloud.squidex.io",
"SQUIDEX_APP": "your-app-name",
"SQUIDEX_CLIENT_ID": "your-app-name:default",
"SQUIDEX_CLIENT_SECRET": "your-client-secret"
}
}
}
}Restart the client after editing.
3. Try it
Ask your assistant something like "List the content schemas in my Squidex app". If it replies with your schemas, it's working.
Alternative: standalone binary (no Node.js needed)
If Node.js/npx isn't available, download a prebuilt binary from the Releases page instead:
OS | File |
Linux (x64) |
|
Linux (ARM64) |
|
macOS (Intel) |
|
macOS (Apple Silicon) |
|
Windows (x64) |
|
Make it executable on macOS/Linux (chmod +x ~/Downloads/squidex-mcp-<your-platform>; macOS may also require xattr -d com.apple.quarantine <file> since it isn't notarized), then use its absolute path as command instead of npx in the config above (and drop the args/-y bits, which are npx-specific).
Profiles (multiple Squidex instances)
If you need more than one Squidex app/instance (e.g. prod + staging) reachable from the same server, use a squidex.config.json file instead of env vars:
{
"defaultProfile": "prod",
"requestTimeoutMs": 15000,
"profiles": {
"prod": { "url": "https://cloud.squidex.io", "app": "blog", "clientId": "...", "clientSecret": "..." },
"staging": { "url": "https://cloud.squidex.io", "app": "blog-s", "clientId": "...", "clientSecret": "..." }
}
}Every tool accepts an optional profile parameter to pick which target to use — no server restart needed to switch. The file is re-read on every call. requestTimeoutMs (default 15000) applies to every Squidex HTTP request across all profiles.
By default the server looks for squidex.config.json in its current working directory; point it elsewhere with the SQUIDEX_MCP_CONFIG env var (absolute path recommended, since the client process's working directory isn't always predictable). If no config file is found at all, the four SQUIDEX_* env vars from Quick start are used as a single implicit default profile.
Content field data must already be shaped per Squidex's partitioning ({ "title": { "iv": "..." } } for invariant fields, { "en": "...", "de": "..." } for localized ones) — call schema_get first to see each field's mode, and language_list to see which language codes are actually configured on the app.
Development
bun install
bun test # unit tests (config, token cache, query builder — no live Squidex needed)
bun run typecheck # tsc --noEmit
bun run dev # start the server with --watch, for local developmentPoint your MCP client at bun run src/index.ts in this directory instead of a downloaded binary while developing.
bun run build produces the Node-targeted dist/index.js that gets published to npm (dependencies stay external — installed normally via npm/npx, not bundled). Separately, bun run build:binary compiles a standalone binary for your current OS only (dist/squidex-mcp); bun run build:binary:all cross-compiles all five release targets at once (dist/squidex-mcp-<platform>) — the same command release.yml runs when a tag is pushed.
Local Squidex for end-to-end testing
docker-compose.yml runs a local Squidex + MongoDB for real (non-mocked) testing:
docker compose up -d # starts Squidex on http://localhost:8085
bun run scripts/e2e-bootstrap.ts # creates a "mcp-test" app + "posts" schema, writes squidex.config.json
bun run scripts/smoke.ts # or drive the tools directly via an MCP cliente2e-bootstrap.ts is idempotent — safe to re-run against an already-bootstrapped instance. It authenticates as the root superadmin client (created via IDENTITY__ADMINCLIENTID/IDENTITY__ADMINCLIENTSECRET in docker-compose.yml, dev-only credentials, not real secrets) and writes a local profile into squidex.config.json.
docker compose down stops it; add -v to also wipe the Mongo volume (fresh Squidex on next up).
Releasing
Pushing a tag matching v*.*.* triggers .github/workflows/release.yml: it runs the test suite, publishes the package to npm, cross-compiles standalone binaries for Linux/macOS/Windows, and attaches them to a GitHub Release.
git tag v0.2.0
git push origin v0.2.0Publishing to npm uses Trusted Publishing (OIDC) — no token/secret needed. One-time setup: publish the first version manually (npm login && npm publish --access public, since Trusted Publisher configuration requires the package to already exist), then on the package's npmjs.com settings add a Trusted Publisher pointing at this repo (francyfox/squidex-mcp) and workflow file (release.yml). After that, every tag push publishes automatically.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
Alicense-qualityBmaintenanceA Model Context Protocol (MCP) server that provides AI assistants with comprehensive tools to interact with Contentful APIs.Last updated13958MIT- FlicenseCquality-maintenanceAn MCP server that enables AI assistants like Cursor and Claude to interact with the Storyblok Management API. It allows users to manage stories, tags, components, assets, and workflows through natural language commands.Last updated7445

Cosmic MCP Serverofficial
AlicenseAqualityCmaintenanceAn MCP server that enables AI assistants to manage content, media, and schemas within Cosmic CMS buckets. It allows users to perform CRUD operations on objects and types while providing tools for AI-driven text, image, and video generation.Last updated17211MIT- Alicense-qualityCmaintenanceOpen-source MCP server that turns any CMS backend into an AI-agent-ready content management system. It provides tools for content CRUD, idea management, and publication tracking, with safety features requiring human approval for publishing.Last updatedMIT
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Markdown-first MCP server for Notion API with 8 composite tools and 39 actions.
MCP server for AI dialogue using various LLM models via AceDataCloud
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/francyfox/squidex-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server