--- title: "A2A 1.0 is six months old. Two-thirds of agent cards still declare 0.3." date: 2026-09-01 summary: "Across the 1,910 version-declaring cards in Agenstry's crawl, 65.5% still say 0.3.x, 41 declare an MCP revision date as their A2A version, and of the 91 signed cards only 52 verify. A field-by-field read of where the public agent web actually is." slug: state-of-the-agent-card author: "Sebastiaan Hilbers" hero_glyph: bars --- A2A 1.0 has been stable since [March 12](https://github.com/a2aproject/A2A/releases/tag/v1.0.0). Six months later, of the 1,910 agent cards in Agenstry's registry that declare a `protocolVersion` at all, [65.5% still declare a 0.3.x version and 25.5% declare any 1.0.x](https://agenstry.com/api/stats). Forty-one declare a version that isn't an A2A version — it's a date, in the exact format the MCP specification uses for its revisions. Nine more declare versions that have never existed in any spec: `1.1`, `1.2`, `2.0`, `5.0`, one lone `9.2.9`. In July, Kin Lane probed 22,341 hosts from the APIs.io catalog and found 65 published agent cards, of which [ten fully conformed to A2A 1.0](https://apievangelist.com/2026/07/29/most-published-agent-cards-are-not-actually-a2a/). His conclusion — "the Agent Card is quietly decoupling from A2A" — was drawn from a small outside-in sample. Our crawl watches the whole public surface continuously, and the full-population numbers say he is measuring something real. The cards parse. What they mostly don't do is speak the current protocol. ## What 1.0 changed, and why the version field is the tell The version story has two earlier chapters. In July 2025, [v0.3.0](https://github.com/a2aproject/A2A/releases/tag/v0.3.0) renamed the card's well-known location from `agent.json` to `agent-card.json` — a small change that doubles as a maintenance probe, because an agent still serving only the old path has not been touched in over a year. In March 2026, [v1.0](https://github.com/a2aproject/A2A/releases/tag/v1.0.0) restructured the card itself: transport moved into `supportedInterfaces[]`, each interface carrying its own `protocolVersion`, and the card gained an optional JWS signature block — the "Signed Agent Cards" the Linux Foundation put at the top of the [one-year announcement](https://www.linuxfoundation.org/press/a2a-protocol-surpasses-150-organizations-lands-in-major-cloud-platforms-and-sees-enterprise-production-use-in-first-year) in April. So the version a card declares is not trivia. It predicts which parsers can read it, whether signature verification is even possible, and whether the deployment is maintained. Here is the declared-version distribution across every card in the registry today: Three details in that distribution deserve more attention than the headline split. **The identity field is where protocol confusion shows up first.** The 41 cards declaring `2025-06-18`, `2025-03-26`, `2025-11-25` or `2026-07-28` are not typos — those are [MCP specification revision dates](https://modelcontextprotocol.io/specification/2026-07-28), pasted into an A2A field. Operators are publishing one manifest and filling its fields from whichever protocol's documentation they read last. Lane saw the same drift from the outside; the version field shows it from the inside. Add the cards declaring `erc8004/1` or a vendor string as their protocol version, and the manifest-first reading gets hard to dismiss: for a meaningful slice of publishers, the Agent Card is a general discovery document, and A2A is one possible thing it might point to. **The legacy path is a quiet unmaintained-deployment census.** [385 of the 2,785 agents whose card path we classify](https://agenstry.com/api/stats) — 13.8% — still serve their card only at the pre-0.3 location the spec renamed fourteen months ago. Lane's outside sample put the same figure at 23%. Whichever end of that range you trust, roughly one card in five to seven has survived two spec generations without its operator touching it. **Signing — the flagship 1.0 trust feature — is where the gap is widest.** Of 6,019 agents with a parseable card, [91 publish a JWS signature block: 1.5%](https://agenstry.com/api/stats). Of those 91, 52 signatures actually verify against a key the domain serves. Six fail verification outright, and 33 sign with a key that can't be fetched at all. In other words: six months after signed cards became the headline feature of the 1.0 release, the number of agents on the public web whose identity claim cryptographically checks out is 52 — and an agent that *attempts* signing has roughly a 43% chance of producing something a verifier can't accept. The feature works; the deployment discipline around key publication doesn't exist yet. ## What this means if you build on agent cards For anyone writing a strict A2A 1.0 client, the numbers are an instruction: a parser that rejects non-conformant cards rejects most of the public agent web. Our own crawler [stopped discarding malformed cards in August](https://agenstry.com/methodology) and instead repairs them field by field, recording each repair as a finding — the strict path had silently blanked 21 real, live agents over a single non-conformant sub-field before we changed it. Verifiers, gateways and registries face the same choice, and the ones that pick strictness will see a much smaller web than the ones that pick salvage-and-annotate. For the A2A project itself, the picture is more encouraging than the 25.5% suggests. The 1.0.x share was zero in March. The [v1.0 migration path](https://github.com/a2aproject/A2A/releases/tag/v1.0.0) was designed to let 0.3 clients keep working, which means there is no forcing function — and version distributions without forcing functions move slowly everywhere. TLS 1.3, HTTP/2 and IPv6 all spent their first years with adoption curves that looked like this. For anyone reading adoption claims: organization counts and card-population measurements are different instruments. [More than 150 organizations back the protocol](https://www.linuxfoundation.org/press/a2a-protocol-surpasses-150-organizations-lands-in-major-cloud-platforms-and-sees-enterprise-production-use-in-first-year), and A2A [joined MCP under the Agentic AI Foundation in August](https://a2a-protocol.org/latest/blog/2026/08/27/a-new-chapter-for-a2a-joining-the-agentic-ai-foundation/). Both facts are real. Neither tells you what fraction of publicly published cards a 1.0 verifier can consume today. That number is 25.5% of the cards that state a version at all — and it is the one this page will keep reporting as it moves. ## What we're watching Three measurements will tell us whether this year's picture is a lag or a plateau. First, the 1.0.x share in the distribution above — if the SDK releases that [quietly ship 1.0 defaults](https://agenstry.com/blog/a2a-compatibility-moved-into-sdks) are doing their job, it should climb without any operator reading a migration guide. Second, the signature verify-rate: 52-of-91 is small enough that a single hosting provider adding key publication to its template would visibly move it. Third, the multi-agent listing format — we began digesting `/.well-known/agents.json` documents this week, and how many agents arrive through listings rather than single cards will say whether the registry-shaped future the [A2A registry proposal](https://github.com/a2aproject/A2A/discussions/741) describes is actually being deployed. ## Sources - [A2A v1.0.0 release](https://github.com/a2aproject/A2A/releases/tag/v1.0.0) — A2A Project, March 12, 2026. - [A2A v0.3.0 release](https://github.com/a2aproject/A2A/releases/tag/v0.3.0) — A2A Project, July 30, 2025. - [Most Published Agent Cards Are Not Actually A2A](https://apievangelist.com/2026/07/29/most-published-agent-cards-are-not-actually-a2a/) — Kin Lane, API Evangelist, July 29, 2026. - [A2A Protocol Surpasses 150 Organizations](https://www.linuxfoundation.org/press/a2a-protocol-surpasses-150-organizations-lands-in-major-cloud-platforms-and-sees-enterprise-production-use-in-first-year) — The Linux Foundation, April 9, 2026. - [A New Chapter for A2A: Joining the Agentic AI Foundation](https://a2a-protocol.org/latest/blog/2026/08/27/a-new-chapter-for-a2a-joining-the-agentic-ai-foundation/) — A2A Project, August 27, 2026. - [MCP specification, 2026-07-28 revision](https://modelcontextprotocol.io/specification/2026-07-28) — Model Context Protocol project, July 28, 2026. - [Agent Registry proposal, discussion #741](https://github.com/a2aproject/A2A/discussions/741) — A2A Project, resolved August 2026. - [Registry statistics API](https://agenstry.com/api/stats) — Agenstry registry crawl, snapshot 2026-09-01. - [State of the Agent Economy](https://agenstry.com/reports/state-of-agent-economy) — Agenstry registry crawl, snapshot 2026-09-01.