MCP became the tool standard for agents — and since December 2025 it no longer belongs to Anthropic
- What it is
- The Model Context Protocol defines, over JSON-RPC 2.0, how a host (the app), a client and servers expose tools, resources and prompts to a model. It was announced by Anthropic in November 2024 and donated in December 2025 to the Agentic AI Foundation, under the Linux Foundation, with AWS, Google, Microsoft, OpenAI and others as members. The current spec revision is from July 2026.
- What was demonstrated
- At donation time the protocol reported 97 million monthly SDK downloads. In August 2026, Google's A2A protocol also joined the foundation.
- What was not
- “Lead maintainer” governance (two, both with Anthropic origins); formal neutrality is recent. Security of third-party MCP servers remains the integrator's problem, not the protocol's.
- Why it matters
- Anyone building agent integrations today builds on MCP; knowing who governs the standard is knowing who your integration depends on.
Appears in trails
Same theme
Agents→Tencent open-sourced a 770B MoE under Apache 2.0 — and it edges Kimi K3 on code with a quarter of the parameters
On real scientific software, the best coding agent solves fewer than half the bugs
ReAct: interleaving reasoning and action is what made the first language agents work
Workflows are not agents: the distinction that prevents most failed agent projects
Get the next Cinco
Tuesday, 7am BRT, in your inbox. Five items, with sources. No daily newsletter, no promotions, and unsubscribing is one click.