@jaydb/mcp
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., "@@jaydb/mcp list documents in the 'users' namespace"
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.
JayDB MCP Server (@jaydb/mcp)
Model Context Protocol (MCP) server for JayDB and JayDB Cloud.
Give AI coding assistants (Cursor, Claude Desktop, Antigravity, Cline) direct access to read, create, update (with optimistic concurrency / CAS), delete, and list documents in your JayDB databases during development.
⚡ Features & Tools Exposed to AI
🔍
jaydb_get: Read documents and view current ETags.✍️
jaydb_put: Create or update documents with optimistic locking (ifMatchCAS orcreateOnly).🗑️
jaydb_delete: Delete documents with ETag safety checks.📋
jaydb_list: List keys and document metadata by prefix.🩺
jaydb_health: Test database connectivity and ping the endpoint.📦 Resource: Access documents directly via URI
jaydb://{namespace}/{key}.
Related MCP server: Jazz MCP Server
🚀 Setup & Configuration
1. Cursor IDE
Add to your .cursor/mcp.json (or Cursor Settings > Features > MCP):
{
"mcpServers": {
"jaydb": {
"command": "npx",
"args": ["-y", "@jaydb/mcp"],
"env": {
"JAYDB_URL": "https://your-tenant.jaydb.com",
"JAYDB_API_KEY": "jcloud_sec_your_api_key_here",
"JAYDB_NAMESPACE": "production"
}
}
}
}For local JayDB development, omit the API key and set JAYDB_URL: "http://localhost:8080".
2. Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"jaydb": {
"command": "npx",
"args": ["-y", "@jaydb/mcp"],
"env": {
"JAYDB_URL": "https://your-tenant.jaydb.com",
"JAYDB_API_KEY": "jcloud_sec_your_api_key_here",
"JAYDB_NAMESPACE": "default"
}
}
}
}🛠️ Environment Variables
Variable | Description | Default |
| Base URL of JayDB Cloud tenant or local JayDB instance |
|
| Server-side API key ( |
|
| Default document namespace/bucket |
|
📄 License
MIT © JayDB
Available Tools
5 toolsjaydb_deleteC
Delete a document from JayDB or JayDB Cloud
Inputs: key (required), ifMatch, namespace.
jaydb_getA
Retrieve a document by key from JayDB or JayDB Cloud
Inputs: key (required), namespace.
jaydb_healthA
Check connectivity and health of the JayDB endpoint
Inputs: baseUrl.
jaydb_listA
List keys and metadata by prefix in JayDB or JayDB Cloud
Inputs: limit, prefix, namespace.
jaydb_putA
Create or update a document with optimistic concurrency control (CAS)
Inputs: key (required), data (required), ifMatch, namespace, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct operation on the JayDB store: get, put, delete, list, and health check. There is no overlap or ambiguity in what each tool does, so an agent should reliably select the right one.
All tools follow the same `jaydb_` prefix and a clear action-oriented name: get, put, delete, list, health. The naming pattern is consistent and predictable, making the tool surface easy to navigate.
Five tools is well-scoped for a key-value document store server. Each tool covers a core operation without unnecessary bloat or missing essentials.
The tool set provides full CRUD coverage through get, put, and delete, plus listing for discovery and health for operational checking. Put explicitly handles both create and update, so no lifecycle gaps are apparent.
Related MCP Connectors
Read, create and update canonical AI-readable documents in your Data Rooms.
The agent-native cloud: database, functions, AI, storage, computers. 53 tools, one API key.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Store, query, and update structured data from any AI agent
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact natively with MongoDB databases, including schema discovery, CRUD operations, aggregation pipelines, and index management via natural language.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to create, read, update, and delete data in local-first apps built with the Jazz framework, with support for sync, auth, and rich data types.1MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to directly manage database tables, execute SQL, and handle user operations in iadev projects from the editor.15MIT
- AlicenseAqualityNot gradedmaintenanceEnables AI assistants to interact with 4D databases via REST API, supporting authentication, schema inspection, data querying, manipulation, and ORDA function calls.6ISC