@dani_avila7: Ok, this is big! MCP now defines an extension specifically for discovering and loading Agent Skills from MCP servers (S…
Summary
The Model Context Protocol (MCP) has introduced an experimental extension for discovering and loading agent skills from servers, enabling dynamic context usage and better orchestration in AI workflows.
View Cached Full Text
Cached at: 09/15/26, 05:44 AM
Ok, this is big!
MCP now defines an extension specifically for discovering and loading Agent Skills from MCP servers
(Save this, It’s worth reading how it works)
The flow is pretty simple:
- MCP Server
- Discover available Skills
- Get Skill metadata
- Load the SKILL.md only when needed
This is a huge step for better context window usage
Instead of loading everything upfront, the agent can discover Skills and load only the one it needs from the MCP
Great progress from the Model Context Protocol team! 👏
modelcontextprotocol/ext-skills
Source: https://github.com/modelcontextprotocol/ext-skills
Skills Over MCP Working Group
⚠️ Experimental — This repository is an incubation space for the Skills Over MCP Working Group. Contents are exploratory and do not represent official MCP specifications or recommendations.
📄 SEP-2640 (Skills Extension): modelcontextprotocol#2640 — the source of truth for the v1 spec text. Review and comments belong on the PR. The copy in this repo is a synced baseline for discussion; see docs/sep-draft-skills-extension.md.
Charter: modelcontextprotocol.io/community/skills-over-mcp/charter — mission, scope, membership, active work items, and success criteria.
Project board: Skills Over MCP WG
Meeting notes: Skills Over MCP WG discussions
Discord: #skills-over-mcp-wg
Open work: Pull requests — proposals, decisions, implementations, and other in-flight contributions welcome.
Why Skills Over MCP?
MCP servers give agents tools, but tools alone are insufficient for complex workflows — tool descriptions tell an agent what a tool does, not how to orchestrate multiple tools to achieve a goal. Skills bridge this gap. They are structured “how-to” knowledge: multi-step workflows, conditional logic, and orchestration instructions that can run to hundreds of lines.
Skills are context, and MCP is a context protocol. Agents already connect to remote services over MCP to get tools — they can get the know-how to use those tools through the same channel. A remote MCP server can serve both its tools and the instructions for using them together, as a single atomic unit. This also enables automatic discovery (connect to a server, find its skills), dynamic updates (server-side changes flow without reinstall), multi-server composition (skills orchestrating tools across servers), and enterprise distribution (RBAC, multi-tenant, version-adaptive content) — all through infrastructure MCP servers already provide.
See why-and-when.md for the full value proposition and a guide for when MCP distribution applies vs. simpler alternatives. For an accessible external framing of the premise, see Angie Jones’s “Skills Over MCP” (Agentic AI Foundation) — “ship the manual with the product.”
Problem Statement
Native “skills” support in host applications demonstrates demand for rich workflow instructions, but there’s no convention for exposing equivalent functionality through MCP primitives. Current limitations include:
- Server instructions load only at initialization — new or updated skills require re-initializing the server
- Complex workflows exceed practical instruction size — some skills require hundreds of lines of markdown with references to bundled files
- No discovery mechanism — users installing MCP servers don’t know if there’s a corresponding skill they should also install
- Multi-server orchestration — skills may need to coordinate tools from multiple servers
See problem-statement.md for full details.
Repository Contents
| Document | Description |
|---|---|
| Problem Statement | Current limitations and gaps |
| Why Skills Over MCP? | Value proposition and decision guide |
| Use Cases | Key use cases driving this work |
| Approaches | Approaches being explored (not mutually exclusive) |
| SEP-2640: Skills Extension | Proposal to serve skills over MCP via the Resources primitive. The v1 baseline text is kept at docs/sep-draft-skills-extension.md, synced from the canonical SEP. Comments and review of v1 happen on the PR; changes beyond v1 are proposed as entries in the decision log. |
| Open Questions | Unresolved questions with community input (see also issues and meeting notes) |
| Experimental Findings | Results from implementations and testing |
| Related Work | SEPs, implementations, and external resources |
| Threat Model | Threat model for skills served over MCP (SEP-2640), with delivery-model recommendations and an archive appendix |
| Skills Extension Candidates | MCP servers, dev tools, SDKs, and skills repositories that are candidates for adopting the skills extension |
| Client MCP Support | Survey of model-facing MCP resource loading and SEP-2640 support across open-source clients |
| Decision Log | Record of key decisions with context and rationale |
| Rationale | Design rationale for SEP-2640’s Resources-based skills extension |
| Glossary | Working definitions for key Skills Over MCP terms |
Contributing
See CONTRIBUTING.md for how to participate.
Similar Articles
@akshay_pachaar: MCP meets agent skills MCP already gave agents a standard way to connect to tools, resources, and external systems. Now…
MCP now defines a standard extension for agent skills, enabling on-demand discovery and loading of reusable workflows for AI agents through existing resources.
@swyx: explain this
This article explains the Model Context Protocol (MCP) for building pluggable AI agent architectures, detailing lessons from building an MCP server at Sentry, including OAuth 2.1 integration, designing agent-friendly tool interfaces, and current ecosystem limitations.
@jakevin7: MCP first tackled: "How does the model discover and invoke tools?" Previously, we worked on Tool schema, but many issue…
The article discusses MCP 2.0's new Skills Extension aimed at improving tool discovery and invocation for AI models, but notes that SDK support has not yet been updated.
AI’s most important protocol is getting a little bit easier to use
The Model Context Protocol (MCP) is getting an update to adopt a stateless approach, eliminating session ID management issues and making it easier to run at scale across multiple servers, which could boost enterprise AI agent adoption.
Code execution with MCP: Building more efficient agents
This article from Anthropic explores how integrating code execution with the Model Context Protocol (MCP) can improve the efficiency of AI agents. It addresses challenges like token overload from tool definitions and intermediate results, proposing code execution as a solution to reduce latency and costs.