News
CAPACITY TEST:

Linux Foundation Executives Put MCP Between AI Models And Enterprise Tools

Newsroom brief

Linux Foundation executives described MCP as a coordination layer that connects AI models to tools, memory and private data, while leaving approved registry lists and production outcomes outside the public record.

Verified against source materialEdited by SendTech Times AI & Enterprise Desk
Linux Foundation Executives Put MCP Between AI Models And Enterprise Tools
Image source: EE Times / Ram Iyengar image

MCP Sits Above The Model Layer

Linux Foundation executives are positioning Model Context Protocol as a coordination layer between AI models and the tools, memory systems, APIs and enterprise data those models need in production.

Anthropic introduced MCP, and governance now sits with the Agentic AI Foundation under the Linux Foundation.

Ram Iyengar, chief evangelist at Cloud Foundry Foundation, said MCP changed how large language models discover tools and capabilities.

He described the protocol as a standard way for LLMs to interact with tools and services through APIs, breaking a prompt into multiple tool calls and skills.

MCP does not replace the model.

It sits above individual components and gives AI systems a way to discover tools, invoke services and handle memory without stuffing every detail into the model prompt.

Registries And Gateways Control Tool Access

Iyengar said MCP registries, gateways, allowlists and blocklists can govern which tools an AI system may access.

He also said anyone can write an MCP, while the Linux Foundation recommends certain registries without maintaining a formal approved-tools list.

Arpit Joshipura, general manager of networking, IoT and edge at the Linux Foundation, linked the open protocol to vendor-lock-in concerns.

He said open protocols let organizations change technology providers without changing the way models connect to tools and services.

Joshipura described AI systems as layered architectures made up of an intelligence layer, an agentic layer and a domain layer.

He said the agentic layer can access public and private data, while organizations configure agents around enterprise requirements and sensitive information.

Goose Shows The Deployment Trade-Off

Iyengar used Goose as one example of MCP implementation.

He said the open-source agent draws on multiple familiar AI tools, including Anthropic Claude, OpenCode and Codex, and has about 128,000 tokens available per session.

Iyengar said Goose can operate on local infrastructure while supporting Ollama, OpenAI, Anthropic’s Claude and Gemini.

He also said sensitive-data organizations could run it in air-gapped environments using local databases, local runtimes and local models.

The deployment examples show why MCP is being discussed as an enterprise control layer rather than only a developer convenience.

The same model may need memory, tool discovery, policy limits and private-data access before it can operate inside a company workflow.

The executives did not name enterprise deployments, audited cost savings or a formal Linux Foundation list of approved MCP tools.

The public record also does not disclose customer production results from Goose or other MCP-based enterprise deployments.

Share this article
inXf

Related articles

More
NVIDIA Agent Toolkit Adds Runtime Controls But No Rollout Counts
AI

NVIDIA Agent Toolkit Adds Runtime Controls But No Rollout Counts

NVIDIA is packaging Nemotron open models, NemoClaw blueprints and OpenShell runtime support for specialized enterprise agents, but the company did not disclose pricing, deployment dates or rollout counts.

Philippines Google Cloud Deal Links Agentic AI To Public Services And Data Routes
AI

Philippines Google Cloud Deal Links Agentic AI To Public Services And Data Routes

The Philippine government has expanded its Google Cloud collaboration to bring enterprise AI into public services while tying the work to cyberdefense cooperation and links between subsea cable systems and domestic networks.

MRAgent Cuts Long-Memory Agent Queries To 118k Tokens In Benchmark Tests
AI

MRAgent Cuts Long-Memory Agent Queries To 118k Tokens In Benchmark Tests

National University of Singapore researchers built MRAgent to reconstruct memory through a Cue-Tag-Content graph, with VentureBeat citing LongMemEval prompt use of 118k tokens per sample versus 632k for A-Mem and 3.26 million for LangMem.

Qualcomm Names Meta As First Dragonfly Data Center CPU Customer
Chips & Semiconductors

Qualcomm Names Meta As First Dragonfly Data Center CPU Customer

Qualcomm said Meta will use its Dragonfly C1000 data center CPU when production starts in 2028, while the chipmaker raised its fiscal 2029 non-handset revenue projection to $40 billion.

Keep Reading

More Stories

Latest
MGX Raises $49bn Fund As Abu Dhabi AI Capital Targets Compute AssetsAIJul 1, 2026MGX Raises $49bn Fund As Abu Dhabi AI Capital Targets Compute AssetsMGX closed its first AI-focused fund at $49 billion, above its $45 billion target, as the Abu Dhabi firm ties sovereign capital to semiconductors, data centres and AI platforms. The company has not disclosed Fund I's investor list, stake sizes or customer capacity commitments.Taiwan Crypto Law Sets FSC Licences And 100% Stablecoin ReservesFintech & Digital PaymentsJul 1, 2026Taiwan Crypto Law Sets FSC Licences And 100% Stablecoin ReservesTaiwan approved the Virtual Asset Service Act, requiring crypto platforms to obtain FSC licenses while stablecoin operators face central-bank approval and 100% reserves. The law sets penalties, but the start date and first approvals remain unnamed.Qatar Funds Turksat Satellite As 50Gbps Capacity Stays At Turkish Orbital SlotTelco & ConnectivityJul 1, 2026Qatar Funds Turksat Satellite As 50Gbps Capacity Stays At Turkish Orbital SlotTurksat and Qatar's Es'hailSat signed a satellite partnership funded by Qatar, with Turkey keeping the 50 degrees east orbital and frequency rights while the project leaves cost, launch timing and customers undisclosed.US Lifts Anthropic Model Export Controls After Safeguards DealCapital & PolicyJul 1, 2026US Lifts Anthropic Model Export Controls After Safeguards DealThe Commerce Department is removing licence requirements for Anthropic’s Mythos and Fable models after a safeguards agreement, reopening foreign access while leaving jailbreak controls as the unresolved policy test.Rocket Lab Sets $8bn Iridium Deal As Satellite Network Test Awaits RegulatorsCapital & PolicyJul 1, 2026Rocket Lab Sets $8bn Iridium Deal As Satellite Network Test Awaits RegulatorsRocket Lab has agreed to buy Iridium Communications for about $8bn, pairing launch and spacecraft manufacturing with a satellite communications network that serves more than 2.55 million active subscribers.Qualcomm AI250 Stacks DRAM Over Compute But Leaves FLOPS UndisclosedChips & SemiconductorsJul 1, 2026Qualcomm AI250 Stacks DRAM Over Compute But Leaves FLOPS UndisclosedQualcomm is pitching high-bandwidth compute for AI inference, with AI250 cards claiming 768 GB of memory and 133 TB/s of effective bandwidth, but the company has not disclosed peak FLOPS or named customers.SEC Chair Says Tokenized Deposits Could Get Approval Next YearFintech & Digital PaymentsJul 1, 2026SEC Chair Says Tokenized Deposits Could Get Approval Next YearSEC Chair Paul Atkins said regulators could approve tokenized deposits as soon as next year, while also tying crypto rulemaking to bank-capital talks with the Fed, FDIC and OCC.UAE AI Authority Consolidates Data And Digital Government MandatesCapital & PolicyJul 1, 2026UAE AI Authority Consolidates Data And Digital Government MandatesThe UAE will establish an Artificial Intelligence and Data Authority to consolidate federal AI, public data and digital government functions, but the government has not disclosed a budget, staffing plan or implementation timetable.Aarogya Setu 2.0 Adds Google Gemma For India Health RecordsCapital & PolicyJul 1, 2026Aarogya Setu 2.0 Adds Google Gemma For India Health RecordsIndia launched Aarogya Setu 2.0 on June 29, 2026 as an AI-enabled personal health-record app using Google Gemma and a medical data toolkit, but public materials have not named an independent privacy audit or model-risk assessment.Saudi PIF Profit Doubles As Revenue Reaches $119.7 BillionCapital & PolicyJul 1, 2026Saudi PIF Profit Doubles As Revenue Reaches $119.7 BillionPIF’s 2025 annual results said net profit rose to SAR65.1 billion and revenue reached SAR449.9 billion, giving Saudi Arabia’s sovereign fund more liquidity for Vision 2030 investments without naming project-level allocations.US Energy Chief Tells Data Center Builders To Answer Power CriticsCloud & Data CentersJul 1, 2026US Energy Chief Tells Data Center Builders To Answer Power CriticsUS Energy Secretary Chris Wright used an AWS Summit appearance to tell data center supporters to engage critics over electricity costs and local opposition as AI construction raises power and permitting pressure.Open USD Consortium Draws Visa, Mastercard And Stripe BackingFintech & Digital PaymentsJul 1, 2026Open USD Consortium Draws Visa, Mastercard And Stripe BackingOpen Standard says more than 140 banks, fintechs, payment companies and crypto firms are backing Open USD, a dollar-backed stablecoin planned for later this year, but the group has not disclosed transaction volumes or customer commitments.