{
"mcpServers": {
"opti-mcp-server": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 17 days ago.
Will it work with my client?
Transport: sse, http. Compatibility not confirmed.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Opti Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
⚠️ Development tool only — do not use in production
This package is intended exclusively for local development against a local database. It exposes unauthenticated content read/write operations over HTTP. Running it in a production or shared environment is a serious security risk and is strongly discouraged.
An MCP (Model Context Protocol) server library for Optimizely CMS 12. Install it into your local Optimizely development project to expose content operations as tools callable by AI assistants (Claude, Copilot, etc.).
Exposes the following MCP tools over HTTP (/mcp):
| Tool | Description |
|------|-------------|
| get_content | Fetch a single content item by ID |
| get_children | List children of a content node (paginated) |
| get_ancestors | Get the breadcrumb hierarchy for a content item |
| get_content_types | List all registered content types and their properties |
| create_content | Create a new content item (draft) |
| update_content | Update properties on an existing content item |
| publish_content | Publish a content item |
| move_to_trash | Soft-delete a content item |
| resolve_url | Resolve a friendly URL to a content reference |
Two guided prompts help AI assistants scaffold the correct tool calls:
create_page — lists available page types and generates a creation workflowcreate_block — lists available block types and generates a creation workflowInstall this package only in your development project configuration (e.g. guarded by
#if DEBUGor an environment check). Never deploy it to staging or production.
dotnet add package Hangsolow.OptiMcpServer
Startup.cs (traditional Optimizely bootstrap)using OptiMcpServer;
public class Startup
{
private readonly IConfiguration _configuration;
public Startup(IConfiguration configuration)
{
_configuration = configuration;
}
public void ConfigureServices(IServiceCollection services)
{
services.AddCms()
.AddOptiMcpServer(_configuration);
}
public void Configure(IApplicationBuilder app)
{
app.UseRouting();
app.UseEndpoints(endpoints =>
{
endpoints.MapDefaultControllerRoute();
endpoints.MapMcp("/mcp"); // exposes /mcp
});
}
}
AddOptiMcpServer returns an IMcpServerBuilder, so you can chain additional tool assemblies:
services.AddCms()
.AddOptiMcpServer(_configuration)
.WithToolsFromAssembly(typeof(MyCustomTool).Assembly);
appsettings.json{
"ConnectionStrings": {
"EPiServerDB": "Server=.;Database=MyDb;Integrated Security=True;TrustServerCertificate=True"
},
"OptiMcpServer": {
"PageBaseClass": "EPiServer.Core.PageData",
"BlockBaseClass": "EPiServer.Core.BlockData"
}
}
Set PageBaseClass and BlockBaseClass to your site's abstract base types (e.g. MySite.Models.Pages.SitePageData) so the create_page and create_block prompts only surface content types relevant to your project.
Once running, the MCP server is available at:
http://<host>/mcp
Configure your AI client to connect to this URL using the Streamable HTTP transport.
This project is licensed under the MIT License — see the LICENSE file for the full text.
Disclaimer: This package is provided "as is", without warranty of any kind. Use it at your own risk. The author(s) accept no liability for any damage, data loss, or other issues arising from its use in any environment, including production Optimizely CMS installations.