[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fUxZEdxzIEl_X-5QL9e4PV1uB0fuHAohyN4CL-CG0cao":3},{"article":4,"iocs":53,"watch_terms":64,"solutions":65,"lesson":126},{"id":5,"title":6,"slug":7,"summary":8,"ai_summary":9,"brief":10,"url":11,"image_url":12,"published_at":13,"ingested_at":14,"relevance_score":15,"entities":16,"category_id":30,"category":31,"article_tags":35},"5c048b4a-c078-4b1c-8321-88b361aba0c2","New Enterprise-Ready MCP Specification Brings New Security Challenges","new-enterprise-ready-mcp-specification-brings-new-security-challenges-6d1db5","A major overhaul of the Model Context Protocol shifts critical security responsibilities from the protocol itself to developers and platform operators. The post New Enterprise-Ready MCP Specification Brings New Security Challenges appeared first on SecurityWeek.","The Model Context Protocol (MCP) is updating to an enterprise-ready, stateless version, shifting security responsibilities from the protocol to developers and operators. While it eliminates some older vulnerabilities, the new MCP introduces risks like state tracking identifier misuse, data leakage via HTTP headers, XSS via MCP Apps, and denial-of-service attacks through long-running tasks.","New enterprise-ready MCP spec shifts security to developers, creating new risks.","https:\u002F\u002Fwww.securityweek.com\u002Fnew-enterprise-ready-mcp-specification-brings-new-security-challenges\u002F","https:\u002F\u002Fwww.securityweek.com\u002Fwp-content\u002Fuploads\u002F2026\u002F04\u002FMCP_Vulnerability.jpg","2026-06-26T08:00:00+00:00","2026-06-26T08:00:23.779199+00:00",7,[17,20,23,25,28],{"name":18,"type":19},"Model Context Protocol (MCP)","product",{"name":21,"type":22},"Anthropic","vendor",{"name":24,"type":22},"Akamai",{"name":26,"type":27},"AI agents","technology",{"name":29,"type":27},"cloud-native AI","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":30,"icon":32,"name":33,"slug":34},null,"Vulnerabilities","vulnerabilities",[36,41,43,48],{"category":37},{"id":38,"icon":32,"name":39,"slug":40},"26b0b636-0e31-4db1-bffb-61bdf9f20a58","Supply Chain","supply-chain",{"category":42},{"id":30,"icon":32,"name":33,"slug":34},{"category":44},{"id":45,"icon":32,"name":46,"slug":47},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",{"category":49},{"id":50,"icon":32,"name":51,"slug":52},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[54,58,61],{"type":55,"value":56,"context":57},"mitre_attack","T1537","Data Leakage via x-mcp-header",{"type":55,"value":59,"context":60},"T1190","Exploitation of Existing Vulnerabilities (XSS via MCP Apps)",{"type":55,"value":62,"context":63},"T1499","Denial of Service (Long-running tasks)",[21,24,18],{"controls":66,"vendors":120},[67,95],{"slug":47,"name":68,"problem":69,"products":70},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[71,79,87],{"vendor_slug":72,"vendor_name":73,"vendor_logo":74,"product_slug":75,"product_name":76,"url":77,"description":78},"boomi","Boomi","\u002Fvendor-logos\u002Fboomi.png","boomi-agentstudio","Boomi Agentstudio","https:\u002F\u002Fboomi.com\u002Fplatform\u002Fagentstudio\u002F","Agent builder whose Agent Control Tower registers and monitors Boomi agents and agents on Amazon Bedrock, Microsoft Copilot and other platforms, keeps audit logs and can switch agents off where the provider allows it.",{"vendor_slug":80,"vendor_name":81,"vendor_logo":82,"product_slug":83,"product_name":84,"url":85,"description":86},"hiddenlayer","HiddenLayer","\u002Fvendor-logos\u002Fhiddenlayer.png","hiddenlayer-ai-security","HiddenLayer AI Security Platform","https:\u002F\u002Fhiddenlayer.com\u002F","Model scanning, AI red teaming and runtime protection for AI applications.",{"vendor_slug":88,"vendor_name":89,"vendor_logo":90,"product_slug":91,"product_name":92,"url":93,"description":94},"palo-alto-networks","Palo Alto Networks","\u002Fvendor-logos\u002Fpalo-alto-networks.png","prisma-airs","Prisma AIRS","https:\u002F\u002Fwww.paloaltonetworks.com\u002Fai-security\u002Fprisma-airs","Security for AI applications, models and agents, including runtime protection against prompt injection.",{"slug":96,"name":97,"problem":98,"products":99},"security-awareness-training","Security awareness training and phishing simulation","People recognise and report attacks instead of falling for them.",[100,106,113],{"vendor_slug":101,"vendor_name":102,"vendor_logo":103,"product_slug":101,"product_name":102,"url":104,"description":105},"hoxhunt","Hoxhunt","\u002Fvendor-logos\u002Fhoxhunt.png","https:\u002F\u002Fhoxhunt.com\u002F","Adaptive phishing simulations and micro-training, with a focus on reporting.",{"vendor_slug":107,"vendor_name":108,"vendor_logo":109,"product_slug":96,"product_name":110,"url":111,"description":112},"knowbe4","KnowBe4","\u002Fvendor-logos\u002Fknowbe4.png","KnowBe4 Security Awareness Training","https:\u002F\u002Fwww.knowbe4.com\u002Fproducts\u002Fsecurity-awareness-training","Training library and simulated phishing with reporting.",{"vendor_slug":114,"vendor_name":115,"vendor_logo":116,"product_slug":114,"product_name":117,"url":118,"description":119},"sosafe","SoSafe","\u002Fvendor-logos\u002Fsosafe.png","SoSafe Awareness Platform","https:\u002F\u002Fsosafe-awareness.com\u002F","Behaviour-based awareness training and phishing simulation in many languages.",[121],{"slug":122,"name":24,"logo_path":123,"roles":124},"akamai","\u002Fvendor-logos\u002Fakamai.png",[125],"reported_by",{"slug":127,"title":128,"body":129,"framework_refs":130,"framework_notes":140},"new-mcp-specification-shifts-security-burden-to-developers-introducing-fresh-risks","New MCP Specification Shifts Security Burden to Developers, Introducing Fresh Risks","The updated Model Context Protocol (MCP) transitions to a stateless, enterprise-ready architecture, but in doing so it offloads critical security responsibilities onto developers and operators rather than enforcing protections at the protocol level. This design shift means that misconfigurations, poor coding practices, and lack of awareness can directly introduce vulnerabilities such as XSS, data leakage via HTTP headers, state tracking identifier misuse, and denial-of-service exposure. The risk is particularly acute because many developers may assume the protocol itself provides safety guarantees it no longer does. As AI-integrated protocols like MCP become foundational enterprise infrastructure, the security posture of every deployment becomes only as strong as the team implementing it.",[131,132,133,134,135,136,137,138,139],"CIS Control 4: Secure Configuration of Enterprise Assets and Software","CIS Control 16: Application Software Security","NIST SP 800-53 SI-10: Information Input Validation","NIST SP 800-53 SC-8: Transmission Confidentiality and Integrity","NIST SP 800-53 SA-11: Developer Testing and Evaluation","OWASP Top 10: A03 Injection \u002F A05 Security Misconfiguration","NIST AI RMF: Govern 1.2, Map 5.1 (AI Risk Management Framework)","GDPR Article 25: Data Protection by Design and by Default","NIST SP 800-95: Guide to Secure Web Services",{}]