@tootega/dase-mcp
Proxy server that enables Claude Code to interact with the DASE ORM Designer VS Code extension, providing 42 tools for database design and management.
README
@tootega/dase-mcp
Standalone MCP (Model Context Protocol) server for the DASE ORM Designer. The full MCP implementation — server, 43 tools, protocol handling — lives HERE, outside VS Code. The DASE extension carries no MCP code at all: it only exposes a loopback agent bridge (plain JSON over HTTP) that this server discovers and drives.
Deliverables:
- Standalone stdio MCP server (
src/server/, built todist/and bundled toclaude-plugin/server/dase-mcp.cjs) — registers the whole DASE tool set; each tool call becomes one HTTP round trip to the bridge. - Claude Code plugin (
claude-plugin/) — publishes that server as an installable plugin.
How it works
Claude Code ──stdio──> dase-mcp server ──HTTP (dase-bridge/1)──> DASE agent bridge (VS Code)
│ discovery: bridge-endpoint.<hash>.json │
└── globalStorage/hermessilva.dase ◄──── written by ─────┘
The DASE extension (setting dase.agentBridge.enabled, on by default) binds an ephemeral
loopback port and writes discovery files (url + protocol + workspacePath + pid) into
its global storage. This server picks the live window whose workspace matches the client's
working directory, connects lazily, and re-discovers + retries once when a call fails (e.g.
the ephemeral port changed after a VS Code reload). When no DASE window is up, tool calls
fail with instructions and the dase_status tool reports connectivity.
Bridge protocol: POST /bridge with { "method": "...", "args": [...] } →
{ "ok": true, "result": ... } or { "ok": false, "error": "..." }. GET /bridge lists the
available methods.
Overrides: DASE_BRIDGE_URL (skip discovery), DASE_MCP_DISCOVERY_DIR (extra discovery directory).
Build
npm install
npm run build # tsc (dist/) + esbuild bundle (claude-plugin/server/dase-mcp.cjs)
node scripts/smoke-test.cjs # fake bridge + stdio round trip
claude-plugin/server/dase-mcp.cjs is a committed build artifact — plugin installs clone the repo and must not need npm install.
Install as a Claude Code plugin
/plugin marketplace add <this repo>
/plugin install dase-mcp
The marketplace manifest is .claude-plugin/marketplace.json (points at ./claude-plugin).
Tool surface
43 tools (12 read, 23 write/mutation, 7 command triggers, 1 status) — see docs/MCP_API_SPEC.md. Integration and security notes: docs/MCP_INTEGRATION.md.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.