Stateless: The Future of MCP Transports

This blog post from the Agentic AI Foundation (AAIF) summarizes a talk by Shaun Smith (Hugging Face) and Kurtis Van Gent (Google Cloud) at the MCP Dev Summit North America 2026 about making the Model Context Protocol stateless. The motivation comes from operational scale: Google Cloud supports MCP servers for AlloyDB, Spanner, Cloud SQL, Bigtable, and Firestore, while Hugging Face runs over 2,500 MCP servers via Spaces and manages over 20 million tool calls across 40+ databases in a single month, with a single tool call generating over 100 MCP protocol messages. The core problem is that MCP is currently stateful, requiring initialization handshakes and persistent session context, which breaks down behind load balancers where requests can arrive at any server. The proposed solutions include: SEP-1442 (removing the initialization handshake as a required first step, folding protocol negotiation into the first actual request like tools/list), SEP-2322 (fixing elicitation by making it a sequence of independent requests where state travels in the payload rather than requiring coordinated servers), moving toward a session-free protocol by default with explicit resource handles passed as tool call parameters, and SEP-2243 (HTTP standardization mirroring JSON-RPC fields into HTTP headers so load balancers can route without parsing payloads). The transport changes are on track for the June spec release, with SEPs landing in April followed by two months of SDK implementation. Future work includes eTags for resource freshness, TTL hints on tool lists, and pluggable transports for WebSockets and gRPC. The working group operates under the Agentic AI Foundation. 

https://aaif.io/blog/stateless-the-future-of-mcp-transports/

Comments

Post a Comment

Popular posts from this blog

Prompt Engineering Demands Rigorous Evaluation

In the blog post “Prompt Engineering Requires Evaluation” on the Shostack + Associates website, the author argues that treating prompts for large language models (LLMs) merely as creative artefacts is insufficient. Engineering prompts properly demands structured evaluation frameworks — what the AI community calls “evals” — to test which prompt versions work better, with which models, and under which conditions. The post highlights that simply assuming a prompt is “good enough” creates risks when LLMs are integrated into production systems (e.g., for threat modeling). It advocates for measuring prompt performance, variation effects, and tool-chain dependencies (model, context, ancillary materials).  Ultimately the message is: prompt engineering should borrow disciplined practices from software engineering (versioning, testing, benchmarking) rather than relying on informal experimentation.  https://shostack.org/blog/prompt-enignieering-requires-evaluation/
Read more

SecObserve: Simplified Vulnerability and License Management for CI/CD Pipelines

 SecObserve is an open-source tool for managing vulnerabilities and licenses in software development and cloud environments. It integrates various vulnerability scanners into CI/CD pipelines using GitLab CI templates and GitHub Actions for streamlined setup. It offers a centralized dashboard for assessing and reporting vulnerabilities, with tools for filtering, sorting, and evaluating results. SecObserve supports automation and manual assessments to focus on resolving critical issues.  https://github.com/MaibornWolff/SecObserve/tree/dev
Read more

Secure Vibe Coding Guide: Best Practices for Writing Secure Code

Ken Huang's "Secure Vibe Coding Guide" emphasizes the importance of integrating security into the software development lifecycle. The guide provides best practices for writing secure code, including input validation, proper authentication mechanisms, and secure data storage techniques. It also highlights the necessity of regular code reviews and staying updated with the latest security vulnerabilities and patches. By following these guidelines, developers can create applications that are resilient against common security threats and contribute to a safer digital environment.  https://kenhuangus.substack.com/p/secure-vibe-coding-guide
Read more