dy-mcp-demo (dy-mcp)
Uses SQLite as the underlying database for storing all context data, supporting six typed contexts.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
dy-mcp-demo
A public, unauthenticated demo of dy-mcp — an MCP personal-context server. Lets you poke at every tool the server exposes without needing to install or configure anything.
Live at: https://demo-mcp.dyuhaus.com
Open the URL in a browser to see the Editorial-style web companion.
Or point any MCP-aware client (Claude Desktop, Claude Code, etc.) at
https://demo-mcp.dyuhaus.com/mcp— no auth header required.
The data is invented (a fictional writer-developer named "Alex Quinn") and the whole database resets every hour, so feel free to create, edit, or delete anything. You won't break it.
For the real, password-protected server this is cloned from, see dyuhaus/dy-mcp.
What's the same as dy-mcp?
Everything to do with the MCP protocol and the data model:
Six typed contexts:
project,idea,preference,writing_style,skill,general.All 12 tools:
get_personal_context,list_contexts,get_context,add_context,update_context,delete_context,search_contexts,import_project,import_project_section,list_project_files,get_project_file,delete_project_file.All 7 resources under
context://.Same SQLite schema, same storage code, same importer, same HTTP routes.
Related MCP server: MCP Personal Tools Server
What's different?
No auth.
/auth/*,/oauth/*,/.well-known/*, session cookies, password bootstrap — all removed./mcpis open. The web UI boots straight into the dashboard.Hourly reset. A scheduled task wipes the DB and reseeds it with the fictional persona (see
scripts/seed.ts).Default port is 7879 so it can run alongside the main dy-mcp on the same machine.
Web sidebar shows "PUBLIC DEMO" and a "resets hourly" note.
Try it from an MCP client
Claude Code
claude mcp add --transport http dy-mcp-demo https://demo-mcp.dyuhaus.com/mcpClaude Desktop / any config-file client
{
"mcpServers": {
"dy-mcp-demo": {
"transport": "http",
"url": "https://demo-mcp.dyuhaus.com/mcp"
}
}
}curl
# list all tools
curl -sS -X POST https://demo-mcp.dyuhaus.com/mcp \
-H "content-type: application/json" \
-H "accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
# call a tool
curl -sS -X POST https://demo-mcp.dyuhaus.com/mcp \
-H "content-type: application/json" \
-H "accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_personal_context","arguments":{}}}'Run the demo locally
npm install
npm run build
npm run seed # wipe + reseed the demo DB
npm run web:build
npm run start:api # http://localhost:7879The web UI is served at the same port as the API.
Dev loop:
npm run dev:api # backend with tsx watch
npm run web:dev # vite dev server on :5173HTTP endpoints
Method | Path | Body / query |
GET |
| returns |
GET |
|
|
POST |
|
|
GET |
| — |
PATCH |
| any subset of the add body |
DELETE |
| — |
GET |
|
|
GET |
|
|
GET |
| full payload snapshot |
GET |
| catalog of tools + resources (drives the /Tools page) |
GET |
|
|
GET |
| — |
DELETE |
| — |
POST |
|
|
POST |
|
|
POST |
| MCP over Streamable HTTP (stateless, single round-trip) |
Hosting
The included scripts/install-demo-task.ps1 registers two Windows scheduled
tasks:
dy-mcp-demo-api— runs the built server on :7879 at boot.dy-mcp-demo-reset— runsscripts/seed.tsevery hour viatsx.
Point a Cloudflare tunnel at http://localhost:7879 under the hostname of
your choice. See CLAUDE.md for the exact commands.
Environment variables
Variable | Default |
|
|
|
|
|
|
|
|
|
|
| (same origin) |
License
MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP server for live public-data APIs and Skills for AI agents.
Generate contextual prompts and reusable agent skills, evaluate prompts with the 16-dimension Prompt Score, and manage saved work in PromptDrive. Twelve MCP tools also provide authorized access to private Memory for source-grounded answers. Connect over Streamable HTTP using OAuth 2.1 and PKCE. Generation consumes account quota and automatically saves successful results; Memory access follows account permissions and plan limits.
One shared context your team's AI tools read & write over MCP. No re-explaining. Free.
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA demonstration server showing MCP implementation in Python with resource handling, tool operations, and reusable prompts for a simple user/post system with local database.-
- AlicenseBqualityDmaintenanceA simple server implementing the Model Context Protocol (MCP) that exposes personal tools like note-taking for compatible MCP clients or agents.2ISC
- AlicenseNot gradedqualityDmaintenanceA demonstration Model Context Protocol server that includes a web-based interface for managing persistent configurations. It provides foundational tools for greeting, echoing input, and retrieving or updating server settings through MCP.17 npmMIT
- AlicenseNot gradedqualityDmaintenanceA single MCP server that gives Claude, ChatGPT, Codex, and any MCP-compatible AI access to the same personal context via two tools: context_get and context_log.1MIT