Cloud Object Storage

Cloud Object Storage

Learn | Share | Collaborate

Join our expert network to explore key Cloud Object Storage (COS) use cases, exchange best practices, and stay informed on webinars, feature releases, and Partner offerings.


#Cloud
#Cloud
#Data
 View Only
Back to discussions
Expand all | Collapse all

Unlock Scalable AI Tooling with MCP Servers on IBM Cloud Code Engine + IBM Cloud Object Storage

  • 1.  Unlock Scalable AI Tooling with MCP Servers on IBM Cloud Code Engine + IBM Cloud Object Storage

    Posted Mon August 25, 2025 12:25 PM

    Looking to extend your LLMs with real-world capabilities like web fetching and file access? Start with Jeremias Werner's blog-a hands-on guide to deploying Model Context Protocol (MCP) servers on IBM Cloud Code Engine, backed by IBM Cloud Object Storage (COS).

    What You'll Learn:

    • How to deploy MCP servers (mcp-npx-fetch, server-filesystem) as containers on Code Engine.
    • How to expose them via SSE using supergateway for remote LLM access.
    • How to integrate with COS for persistent, scalable, and secure file storage.

    Why It Matters:

    • Code Engine provides serverless, auto-scaling infrastructure-perfect for MCP tools that idle until called.
    • COS enables LLMs to read/write files across sessions, share context between agents, and store outputs securely.
    • Supergateway bridges local MCP tools to HTTP endpoints, making them usable by clients like Claude Desktop and LangChain.

    Use Cases:

    • Summarize live web pages with fetch_txt.
    • Read/write shared documents with read_txt and write_txt.
    • Build enterprise-grade tools that wrap internal services like IBM MQ or Process Mining.

    🔗 Ready to build smarter agents with scalable infrastructure?
    Read the full blog here



    ------------------------------
    Danielle Kingberg
    Sr. GTM Product Manager, IBM Cloud Object Storage
    ------------------------------


Related Content