veda-mcp-app
MCP server for a VEDA STAC catalog, providing a tool to call and interactive React UI to view STAC collections.
README
veda-mcp-app
MCP App (Apps SDK) for a VEDA STAC catalog: an MCP server that registers tools linked to an interactive single-file React UI resource, rendered in a host like Claude Desktop.
Searches the live VEDA STAC API (https://dev.openveda.cloud/api/stac, override
with VEDA_STAC_ROOT) and renders results with @teamimpact/veda-ui-blocks
cards — collections as CardCTA, items as CardDetailed with raster preview
thumbnails. A veda-ui-blocks raster map (from each item's COG asset) comes later.
Tools
search_collections(query?, limit?)— search/list VEDA collections (datasets); optional case-insensitive substring query.list_items(collectionId, limit?, bbox?, datetime?)— list items (dated scenes) in a collection, each with a raster preview and a COG asset.run_demo()— happy path: recentno2-monthly(Nitrogen Dioxide) items with previews. Ask the host to "run a demo of the VEDA MCP app".
Quick start
npm install # auto-builds dist/ (prepare script)
npm run setup:claude # register with Claude Desktop + Claude Code
Restart Claude Desktop (Claude Code picks it up on next launch), then ask it to
"run a demo of the VEDA MCP app". Rebuild with npm run build after code changes.
Scripts
npm run setup:claude— register the server with local Claude hosts (absolute paths, idempotent). Flags:--print,--remove,--desktop-only,--code-only. Re-run after switching node versions.npm test— run unit tests (vitest).npm run build— typecheck + build UI + compile server todist/.npm start— run over HTTP (http://localhost:3001/mcp) for manual testing.npm run serve:stdio/npm run dev— stdio from source / watch mode.
UI preview harness
preview.html renders the collections/items views with fixture data outside
the MCP host, for inspecting card layout in a plain browser:
INPUT=mcp-app.html npx vite --port 3006
# open http://localhost:3006/preview.html
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.