A model context protocol (MCP) server for Umbraco CMS
Umbraco mcp mcp server lets Claude, Cursor and other MCP clients work with Umbraco MCP directly. A model context protocol (MCP) server for Umbraco CMS.
THIS REPO HAS NOW MOVED - https://github.com/umbraco/Umbraco-Cms-MCP-Dev
Once connected, the assistant can call these 3 tools directly:
Project — specific context and architectureUmbraco — In order for the MCP to talk to the Management API you will need to create a API user if you are unsure how to do this follow [Umbraco'sInstallation — First, create an Umbraco API user with appropriate permissions. You can find instructions in [Umbraco'sThe server is distributed via npm as @umbraco-mcp/umbraco-mcp-cms, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Before the server will start you need to supply 5 environment variables: NODE_TLS_REJECT_UNAUTHORIZED, UMBRACO_CLIENT_ID, UMBRACO_CLIENT_SECRET, UMBRACO_BASE_URL, EXCLUDE_MANAGEMENT_TOOLS. Keep credentials in your client's env block or a secrets manager rather than committing them.
Knowledge and memory servers address the most frustrating trait of language models — walking into every conversation with no recollection of the last one. Umbraco MCP sits in that group, and the shape of its toolset — Project, Umbraco, Installation — tells you what it is really for. Worth comparing against the other knowledge memory servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Project | specific context and architecture |
| Umbraco | In order for the MCP to talk to the Management API you will need to create a API user if you are unsure how to do this follow [Umbraco's documentation](https://docs.umbraco.com/umbraco-cms/fundamentals/data/users/api-use |
| Installation | First, create an Umbraco API user with appropriate permissions. You can find instructions in [Umbraco's documentation](https://docs.umbraco.com/umbraco-cms/fundamentals/data/users/api-users). |
{
"mcpServers": {
"umbraco-mcp": {
"command": "npx",
"args": ["@umbraco-mcp/umbraco-mcp-cms@alpha"],
"env": {
"NODE_TLS_REJECT_UNAUTHORIZED": "0",
"UMBRACO_CLIENT_ID": "umbraco-back-office-mcp",
"UMBRACO_CLIENT_SECRET": "1234567890",
"UMBRACO_BASE_URL": "https://localhost:44391"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| NODE_TLS_REJECT_UNAUTHORIZED | Configuration value read at startup. | Optional |
| UMBRACO_CLIENT_ID | Configuration value read at startup. | Optional |
| UMBRACO_CLIENT_SECRET | Credential the server authenticates with. | Yes |
| UMBRACO_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| EXCLUDE_MANAGEMENT_TOOLS | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.