Click on "Deploy 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., "@dandi-query-server Create a note about the motor cortex findings from DANDI Archive"
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.
Enables complex queries over data on the DANDI Archive
This is a TypeScript-based MCP server that implements a simple notes system. It demonstrates core MCP concepts by providing:
Resources representing text notes with URIs and metadata
Tools for creating new notes
Prompts for generating summaries of notes
List and access notes via note:// URIs
Each note has a title, content and metadata
Plain text mime type for simple content access
create_note - Create new text notes
Takes title and content as required parameters
Stores note in server state
summarize_notes - Generate a summary of all stored notes
Includes all note contents as embedded resources
Returns structured prompt for LLM summarization
Related MCP server: lafe-blog MCP Server
Install dependencies:
npm installBuild the server:
npm run buildFor development with auto-rebuild:
npm run watchTo use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"dandi-query-server": {
"command": "/path/to/dandi-query-server/build/index.js"
}
}
}Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspectorThe Inspector will provide a URL to access debugging tools in your browser.
Execute advanced SQL queries against the DANDI database
Inputs: sql (required).
Get available filter options for basic search
Inputs: no named parameters.
Get complete database schema with all tables and their columns
Inputs: no named parameters.
Get database schema information
Inputs: table.
Search DANDI assets (files/sessions) using basic filters
Inputs: limit, offset, species, dandiset_id, +2 more.
Search DANDI datasets using basic filters
Inputs: name, limit, offset, anatomy, +4 more.
Validate SQL query without executing it
Inputs: sql (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Most tools have distinct purposes, but `get_schema` and `get_full_schema` overlap significantly. The descriptions differ in wording but not in clear behavioral distinction, which could confuse an agent.
All tool names follow a consistent `verb_noun` pattern (e.g., `execute_sql`, `search_datasets`). Even `get_full_schema` adheres to this pattern with an adjective inserted. No mixing of conventions.
Seven tools cover querying, schema exploration, and validation. This is a well-scoped set for a database query server—enough tools to be useful without overwhelming the user.
The tool set covers core query, schema, and search needs. Missing conveniences like direct single-resource lookup by ID, but SQL can compensate. Minor gap in not having a tool for retrieving specific dataset details without SQL.
Search and manage your Dexi notes: full-text and semantic search, tags, folders, spaced repetition.
Create, search and manage Knowtis collaborative notes from AI assistants.
Turn your notes, links and conversations into a Living Brain your AI tools share and build on.
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
