Canon term · Protocol

Model Context Protocol

An open protocol connecting AI systems to external data sources and tools through a client-server interface, in which a server exposes a declared set of resources, tools and prompts to a host application's client.

  • StatusIndustry term
  • AdoptionWidely used
  • LayerIntelligence
  • Short formMCP

Why it matters

MCP describes capability, not permission. It answers what an agent can reach, and is silent on what it may commit, under whose authority, and up to what limit.

Where it comes from

Anthropic; published as an open specification.

Defining sources

What it is not

These are routinely confused with Model Context Protocol. The distinctions have consequences for how a system is governed.

  • A2A (Agent2Agent)

    MCP connects an agent to tools and data. A2A connects agents to each other. They operate at different layers and are complementary, not competing.

How it connects

What it needs

  • Model Context Protocol depends on MCP Standard

What relies on it

Not to be confused with

Cite and reuse

Cite the identifier QIS-TERM-00017, not the URL: identifiers are stable, URLs may change. This entry is free to read, quote and index under the dual license. Corrections sent to editor@qisfund.com are published.

Technical details: identifier, graph relationships and record
QIS-TERM-00017: outbound relationships as published in api/graph.json and api/lexicon.json
PredicateTarget identifierTargetPredicate meaning
producesterm:tool-manifestTool ManifestThe subject emits the object as an output.
notEquivalentToterm:a2aAgent2AgentThe two are routinely conflated and are distinct.
dependsOnstd:mcpMCPThe subject cannot function correctly without the object.
Canonical identifier
QIS-TERM-00017
Tier
Canonical industry term
Domain · layer
Protocol · Intelligence
Semantic aliases
None recorded
First published
2026-08-02
Last reviewed
2026-08-02 · 180-day cycle