Francesco Pagliari

The #telecom industry needs to engage rapidly with a new #platform technology called #MCP, which may form a central plank of future #AgenticAI architectures and #APIs. But it should not over-react or over-engineer. I'll do deep-dives later as I learn more, but MCP (Model Context Protocol) is moving so fast it needs immediate attention. It was announced by Anthropic in Nov'24 and has snowballed into a major "thing" In short, MCP servers give AI agents and #LLMs a well-structured description of, and access to, a set of available "resources". This could include APIs, tools, data sources or other AI functions. A common description is that MCP is an abstraction layer or "universal connector" that reduces the need for developers or IT asset owners to manually set up connectors for each of them. It could also be seen as a directory or registry of AI-accessible resources, or even a marketplace or appstore as an analogy. There will be many MCP servers, both in the cloud and in the enterprise's own systems. Some people describe it as being analogous to REST APIs, but designed for agents, with richer descriptions (context). There are also various attempts to create parallel agent-to-agent standards, such as Google's A2A. In telecoms, I see a range of possible uses for MCP: - Internal AI development by telco / vendor AI teams - Agentic discovery & consumption of telco and NetworkAPIs. Critically this could include both standard APIs (eg TM Forum or #CAMARA) and customer / specific APIs, and span telecom and enterprise networks, plus #CPaaS - Interaction with non-telco APIs (eg for specific verticals, apps, or adjacent sectors such as utilities and government) - Enablement of the #B2AI concept I introduced recently & discussed at the July #UnthinkableLab workshop with Andrew Collinson & Charlotte Patrick - MCP agents & servers inside network elements, such as RAN nodes, #5G / #6G core, home gateways, enterprise #WiFi or BNGs. That said, more deterministic (non-LLM / #GenAI) approaches may be more appropriate for low-latency or high-regulatory aspects such as #spectrum management. - *Maybe* a long-term post‑REST paradigm that could create a new AI front-end for systems, if we posit an "agent-native" world. There is already telecom work on MCP, including from TELUS, Telefónica, Vodafone, IETF, Sinch and The Linux Foundation #CAMARAProject Overall: - MCP is not (yet) a silver bullet. It’s a useful abstraction layer for APIs & future "Agentic-native" systems - Telcos should treat MCP as an urgent experiment for now - MCP and B2AI may become mutual catalysts - Security and regulatory concerns are *very* messy here. Beware - We're going to see lots of hybrids of REST, gRPC, MCP etc for different “users”: humans, apps, microservices, AI agents etc - No, telecom won't shape MCP. It's already too late - Laugh at anyone saying "Telco MCP market is worth $xxx billion" More to come from me. It feels important. Get in touch for private advisory & consulting.

305

55 commenti

Why 5G Demands a New Transport Network 5G isn’t just faster - it’s smarter, more diverse, and ultra-responsive. To meet these demands: •Peak data rates: up to 20× higher than 4G •Latency: 10× lower for ultra-reliable low-latency communication (URLLC) To deliver this, the transport network has evolved into three key segments, collectively called xHaul: Fronthaul, Midhaul, and Backhaul. 🔹 Fronthaul: From CPRI to eCPRI •Throughput: up to 50 Gbps •Latency: <0.1 ms •Packet-based, more efficient, carrying only selected functions thanks to DU/RU splitting •Enables flexible deployment of Distributed Units at cell sites or edge nodes 🔹 Midhaul: Connecting DU to CU •Data rates: up to 10 Gbps •Latency: <2 ms •Distance: up to 200 km depending on deployment •Provides flexibility in placing DU/CU based on service or traffic needs 🔹 Backhaul: Linking CU/Edge to Core •Data rates: up to 100 Gbps •Latency: <10 ms •Aggregates traffic from multiple sites •Ensures service continuity, handovers, and core-level policy enforcement 💡 Bottom line: 5G’s xHaul architecture transforms the transport network from a single path in 4G into a segmented, performance-tiered network. eCPRI powers real-time fronthaul Midhaul enables flexible DU-CU placement Robust backhaul ensures the core keeps pace with distributed intelligence at the edge The result? A transport network ready to handle 5G’s speed, scale, and diversity. To learn about 5G evolution, refer to the course - https://lnkd.in/eKKRjTUY #5G #Telecom #xHaul #TransportNetwork #eCPRI #DU #CU #EdgeComputing #NetworkInnovation

98

4 commenti

🔴 eSIM Reality Check and Privacy Leak Researchers exposed that many travel eSIMs silently route traffic through foreign carriers and grant unverified resellers carrier-grade privileges. 📡 It arises from eSIM’s remote-provisioning model, shifting trust to cloud resellers and routing paths, where nontransparent intermediaries operate with fewer safeguards, leaving users vulnerable to potential data leaks. Key findings: 🔻 Cross-border routing. Many travel eSIMs send traffic via foreign networks (ex. Holafly via China Mobile), exposing data to other jurisdictions. 🔻 Third-party access. Unverified resellers can view IDs, track location, assign static IPs, revoke profiles etc - without oversight. 🔻 Silent activity. Some eSIMs quietly open data sessions or receive SMS without user notification. 25 travel eSIMs were tested 🔸 Nearly all routed traffic through foreign networks. 🔸 2 showed silent “phone-home” activity. 🔸 2 reseller platforms exposed carrier-level controls to unverified users. Does the eSIM standard itself have security flaws? No, the standard is technically secure. ⚠️ But actual security depends on all ecosystem parties (SM-DP+, eUICC, MNOs, resellers) acting correctly. The risks come from how controls are redistributed in real-world deployments, where governance and enforcement lag. 🙌 Kudos to researchers from Northeastern University - Maryam Motallebighomi, Jason Veara, Evangelos Bitsikas and Aanjhan Ranganathan. #eSIM #TelecomSecurity #MobileSecurity #Privacy #GSMA #CyberSecurity

3.241

180 commenti

What happens when your BSS doesn’t just process data… but actually thinks? Imagine a platform where: • Customer interactions can be predicted, recommendations are highly tailored and explainable, • Campaigns can be simulated and tested before launch, • AI agents work around the clock, taking safe, autonomous actions across domains, • New AI capabilities can be built in minutes without coding. This isn’t a concept. It’s here! Read our latest article on Developing Telecoms to discover how Agentic AI and Digital Twins are redefining customer engagement for the AI-native era! Click to read: https://lnkd.in/dak74Ynf #etiya #developingtelecoms #agenticai #digitaltwin

118