Extend the Ecosystem, Preserve the Core
MSP-1 is intentionally small. Extensions provide a controlled way to explore additional semantic patterns while keeping the core protocol stable, readable, and broadly implementable.
A good extension should add useful context without creating dependency, enforcement, or protocol bloat.
Extension Principles
Proposed extensions should follow the same discipline as MSP-1 itself: clear scope, conservative claims, graceful degradation, and compatibility with systems that do not recognize the extension.
- Extensions should be optional.
- Extensions should not redefine core MSP-1 terms.
- Extensions should degrade safely when ignored.
- Extensions should avoid enforcement or permissions logic.
- Extensions should be documented clearly enough for developers and agents to interpret.
Extension concepts for or in development.
Discovery / Architecture
Consumption Context Extension
Status: In Development
The Consumption Context Extension proposes a minimal, declarative structure for expressing objective characteristics of a resource that may help an agent or consuming system evaluate it before detailed inspection or consumption. Candidate declarations may include measurable extent, completeness, coverage, source composition, and citation or reference availability where those properties are applicable and not already expressed by the MSP-1 core.
The extension is intended to reduce uncertainty without expressing preference, recommendation, value, price, availability, purchase conditions, or behavioral instructions. Its primary focus is resources that cannot be fully inspected before an access decision, while remaining valid for openly accessible artifacts where the same declarations may support discovery, comparison, or other downstream evaluation.
View Development Page →
Identity / Provenance
Brand Provenance Extension
Status: Concept
Provide an optional, declarative layer for identifying brand authority, origin, affiliation, evidence boundaries, and official representation across agentic systems. Its purpose would not be to optimize recommendation outcomes, assert market leadership, or create a proprietary scoring framework, but to help machines distinguish official brand context from derivative, outdated, unaffiliated, or unsupported representations.
Discovery / Architecture
Asset Discovery Extension
Status: Concept
Introduces an explicit, declarative asset registry that allows publishers to identify the protocols, tools, APIs, knowledge bases, identity anchors, structured data surfaces, and functional capabilities available across a site, page, component, or endpoint.
ADE provides agents with an architectural map of what assets exist, where they are located, what tasks and contexts they support, and how they relate to one another. This helps agents identify a relevant working set before parsing individual payloads, activating runtime environments, or inferring functionality from page structure alone.
ADE remains strictly declarative. It does not invoke tools, authorize actions, define protocol mechanics, or require agents to follow a prescribed path. It gives agents a clearer starting point while leaving execution to the appropriate native system.
Agent Workflow
Agent Handoff Extension
Status: Concept
A proposed structure for declaring task state, intent, context, and interpretive posture when one agent hands work to another agent, model, tool, or workflow stage.
Agent Workflow
Context Compression Extension
Status: Concept
A proposed structure for preserving milestone-level task context so agents can retain meaning, reduce drift, and avoid carrying unnecessary conversational or workflow history.
Identity / Provenance
Media Provenance Extension
Status: Concept
A proposed structure for declaring the origin, edit history, AI involvement, or creative lineage of media assets without turning MSP-1 into an enforcement or rights-management system.
Trust / Calibration
Epistemic Scope Extension
Status: Concept
A proposed structure for declaring the limits, assumptions, uncertainty, recency, or domain boundaries of a model output, document, dataset, or agent-generated artifact.
Candidate Extension Lifecycle
Extensions should mature gradually. An idea may begin as a concept, move into a draft structure, become testable through experiments, and only later be considered for broader documentation or tooling support.
- Identify the semantic gap the extension addresses.
- Confirm that the need does not belong in the MSP-1 core.
- Define a minimal optional structure.
- Test graceful degradation when the extension is ignored.
- Evaluate whether the extension improves interpretation or workflow quality.
- Document implementation guidance and edge cases.
Not a Shortcut to Core Status
An extension is not a request to make the core protocol larger. Labs extensions exist precisely because many useful ideas should remain optional, scoped, and experimental.
This separation allows MSP-1 to evolve around a stable center rather than absorbing every possible use case into its foundation.
