Linux Foundation’s CAMARA project releases MCP white paper

The Linux Foundation’s CAMARA project released a white paper titled “In Concert: Bridging AI Systems & Network Infrastructure through MCP: How to Build Network-Aware Intelligent Applications.” The document set out why connecting Artificial Intelligence (AI) systems with underlying network capabilities matters for the behavior of intelligent applications.

The paper stated that Telco network capabilities exposed through APIs provide a large benefit for customers and that simplifying telco network complexity with APIs across telco networks and countries enabled easy and seamless access. CAMARA described an operator-agnostic, “write once” approach intended to reduce fragmentation and provide uniform access to capabilities such as Quality on Demand, Device Location, Edge Discovery, and fraud prevention signals.

The white paper outlined how the Model Context Protocol (MCP) and CAMARA’s network APIs could supply AI systems with real-time network intelligence. It described an architecture in which an MCP server acted as an abstraction layer that translated CAMARA APIs into MCP-compliant “tools” discoverable and invocable by AI applications, allowing AI agents to dynamically access newly released Application Programming Interface (API) capabilities without continuous code refactoring.

CAMARA documented collaboration with the GSMA Operator Platform Group to align API requirements and publish API definitions, and it described harmonization through working code and developer-friendly documentation. API definitions and reference implementations were made available under the Apache2.0 license. The paper listed objectives for MCP support, and it noted MCP now resides under the Linux Foundation’s Agentic AI Foundation with founding project contributions including Anthropic’s MCP, Block’s goose, and OpenAI’s AGENTS.md and cited more than 10,000 published MCP servers.

“With MCP now under the Linux Foundation’s Agentic AI Foundation, developers can invest with confidence in an open, vendor-neutral standard,” said Arpit Joshipura, general manager, Networking, Edge and Internet of Things (IoT) at the Linux Foundation. “The Agentic AI Foundation calls for trustworthy infrastructure. CAMARA answers that call. As AI shifts from conversation to orchestration, agentic workflows demand synchronization with reality,” said Nick Venezia, CEO and Founder, Centillion.AI, CAMARA End User Council Representative to the Time-Series Compression (TSC).

The organizations described plans to support MCP with security guidelines, standardized MCP tooling for CAMARA APIs, and quality requirements and success factors needed for production-grade implementations.