Another major benefit of Anthropic’s Claude Desktop support for remote MCP servers is the ability to combine powerful data access and visualization in notebooks that can be shared via web links.

OPAL MCP server example: an earlier demo ⤵️

claude.ai/share/11cb40...

What’s happening here?

An A2A Orchestrator is interacting with an LLM-powered AI Agent that exposes procedures, functions, 3rd party APIs etc., as MCP-accessible tools.

All made possible by the, in deceptively simple manner, by the OpenLink AI Layer (OPAL).

#MCP #A2A #GenAI

Here’s an example of A2A and MCP working in concert: a Data Twingler—built from tools that perform SQL or SPARQL queries—responds to requests from an A2A Orchestrator, which receives input from the user.

#MCP #A2A #Screencast #OPAL #SQL #SPARQL #DataSpaces #KnowledgeGraph #DBMS

🧰 This is what modern AI infrastructure looks like.

Here’s a quick showcase featuring AnthropicAI’s Claude Desktop interacting with a live OPAL instance that queries the DBpedia Knowledge Graph—entirely instructed using natural language.

#MCP #OPAL #Screencast

🧠 This isn’t just about AI hype.

It’s a working example of how loosely coupled software, rooted in decades of standards-based middleware and Semantic Web architecture, is making modern AI useful—fast, secure, scalable, and enterprise-grade.

4/N 🧵

⚙️ Deploying to the cloud? It’s simple:

1. Go to the AWS Marketplace
2. Instantiate the OPAL AMI
3. Open {cname}/chat and log in
4. Plug in your favorite LLM API key from providers

Enjoy!

3/N 🧵

💡 Why it matters:

This is software—redefined.
Natural language is now a first-class UI/UX component. Data Spaces—databases, knowledge graphs, and filesystems—are loosely coupled with LLMs.

And it all runs, with ease, where you need it: in the cloud or at the edge.

2/N 🧵

Attached is a simple MCP demo using the new mcp-odbc-server with our multi-model Virtuoso platform for data access, integration, and management.

#MCP #ODBC #VirtuosoRDBMS #SQL #SPARQL #DataConnectivity #LinkedData #HowTo

Historically, software quality has been weakened by the dilution that occurs as conceptual ideas are handed off from specification → coding → QA → documentation—each step involving people with different skill sets, incentives, and interpretations.

A new era begins, where that gap can finally close.

This is the real game-changer that AI introduces—finally making software more powerful and flexible through direct domain expert engagement.

These operations include:

- Native and virtual database queries via SQL, SPASQL, SPARQL, and GraphQL
- Metadata exploration across relational tables and knowledge graphs
- DB Admin & Governance
- Interaction with all bound Large Language Models (LLMs)
- Integration with AI agents
- etc..

On the client side, OPAL can bind to operations (tools) published by any MCP server that supports Streamable HTTP or Server-Sent Events (SSE).

On the server side, its operations (tools) are exposed to any MCP-compliant client.

Here's the prompt:

Using JDBC with the following connection details:

URL: jdbc:oracle:thin:@oracle-host:1521:XE
Credentials: UID=hr, PWD=openlink

Write a query to produce a dashboard summarizing job history by employee.

Link to the Claude Artifact generated: claude.ai/public/artif...

#MCP

Using the MCP services at: awsnews.remotemcp.directory

Operations bound to the services offered via the following Streamable HTTP endpoint:
awsnews.remotemcp.directory

Chat UI Options:
* linkeddata.uriburner.com/chat
* inspect.mcp.garden#chat (via linkeddata.uriburner.com/chat/mcp/mes...)

One more thing, OPAL implements MCP as both a Client and Server, so it can bind to operations (tools) published by other MCP Servers that support SSE or Streamable HTTP.

Links in the next reply for a quick example.

Related Links:

🔗 community.openlinksw.com/t/introducin... -- Introducing the OPAL MCP Server

🔗 community.openlinksw.com/t/openlink-a... -- OPAL Cloud Edition for the Amazon EC2 Cloud

#MCP #OPAL #VirtuosoRDBMS #AI #GenAI

4/ What next?

Take a look at OPAL by:

✅ Deploying it via cloud or on-premise

✅ Building AI-driven assistants for customer support, database queries & more

✅ Upskill your team —end-users, developers, product owners, marketers, & leadership in general