Skip to content

Standard

A2A

Agent2Agent (A2A) is an open protocol, originally backed by Google, letting AI agents built on different frameworks communicate and coordinate tasks.

Known aliases

  • A2A boundary
  • A2A v1.0
  • Agent2Agent
  • Agent2Agent Protocol
  • agent-to-agent protocol

Current stories

buildOne report1 publisher

A2A ships an official CLI after its community and SDK clients drifted apart

A2A has shipped a2a, an official command-line client built from its Go SDK's CLI, as one command surface for every A2A Protocol v1.0 agent. Scripts that broke when moved between drifting community and SDK clients now get one target to code against.

Publishers:a2a-protocol.org

Reality

Evidence40
Adoption
Not scored
Hype gap+15
Incentives65
Confidence50
productConfirmed2 publishers

Google, JPMorgan, Weaviate and two governments shipped the same SSRF flaw in their MCP servers

Syed Anas Mohiuddin found the same SSRF flaw in MCP servers from five unrelated organisations, including Google, JPMorgan and two governments. Each server turned an address supplied through an agent into an outbound request without checking where it resolved, and any team running its own tool servers can check for the same gap.

Reality

Evidence64
Adoption48
Hype gap+22
Incentives40
Confidence62
buildOne report1 publisher

kagent 1.0 swaps Deployment-backed agents for a Postgres-backed gRPC lifecycle object

Roughly 130 pull requests, most of them refactoring, retire the Kubernetes Deployment that used to sit under every kagent agent. The tag string on the release says alpha1 and GitHub's flag on it says prerelease false.

Publishers:dev.to

Reality

Evidence60
Adoption15
Hype gap−10
Incentives40
Confidence55
buildOne report1 publisher

Kubernetes probe defaults treat a 40-second tool call as a hang

A dev.to post works through what the stateless-service playbook does to an agent request. The common probe cadence restarts a pod after roughly 30 seconds of silence on /health, and one slow tool call takes longer than that.

Publishers:dev.to

Reality

Evidence38
Adoption20
Hype gap+30
Incentives60
Confidence45
leadershipOne report1 publisher

Google's AP2 replaces the buy click with a cryptographically signed mandate

Google's Agent Payments Protocol makes an agent's authority to pay a cryptographically signed mandate holding price limits, timing and other conditions. Whoever drafts those conditions is setting spend policy.

Publishers:cloud.google.com

Reality

Evidence40
Adoption
Not scored
Hype gap+30
Incentives80
Confidence60
buildOne report1 publisher

Google's ARD spec stops at the endpoint, before the agent proves which workload is calling

The spec's own boundary list says a verified catalog entry establishes which domain claims a capability and what trust material it published. It says nothing about whether the calling process is the agent it names.

Publishers:dev.to

Reality

Evidence45
Adoption18
Hype gap−10
Incentives30
Confidence45
buildOne report1 publisher

Why bounding the agent loop matters for a Well-Architected review

AWS keeps its six pillars in the new Agentic AI Lens and reads them through five runtime behaviours, which leaves reviewers holding a design whose only enforceable artifact is the set of caps around a loop they cannot draw in advance.

Publishers:dev.to

Reality

Evidence34
Adoption28
Hype gap−12
Incentives38
Confidence42
buildOne report1 publisher

Splitting an ADK graph across A2A workers strands output_key in the worker's session

Google ADK's output_key writes into whichever agent's session declared it, and in-process that session is shared. A branch-coverage gate that only ever runs the single-process topology cannot reach the failing path.

Publishers:dev.to

Reality

Evidence48
Adoption18
Hype gap−12
Incentives58
Confidence46
buildOne report1 publisher

Cloud Run's agent card tells clients to reach the agent at 0.0.0.0:8080

A discovery-only comparison of A2A agents on three clouds, measured in August 2026, found one protocol producing three auth models and one card whose sole declared interface URL is the container's bind address.

Publishers:dev.to

Reality

Evidence58
Adoption
Not scored
Hype gap−5
Incentives32
Confidence55
buildOne report1 publisher

AgentCore charges a second IAM action just to read the agent card, and the card talks

A grant of InvokeAgentRuntime will not fetch an A2A agent card on Bedrock AgentCore. And the card a Strands agent publishes there runs 2,109 bytes, most of it the agent's own instructions.

Publishers:dev.to

Reality

Evidence62
Adoption18
Hype gap+8
Incentives38
Confidence55
buildOne report1 publisher

The A2A card said 0.0.0.0:8080, and the only caller it broke was Google's

One line of Google ADK turns an agent into an A2A server. Deployed to Cloud Run and called from AWS and Azure, it advertised the address it binds instead of the address anyone can dial.

Publishers:dev.to

Reality

Evidence58
Adoption18
Hype gap+8
Incentives32
Confidence54
buildOne report1 publisher

Three clouds, one protocol, no stored credentials: the runtime becomes a swappable part

A Bedrock AgentCore agent serving Google and Azure callers over A2A pushes the vendor-specific work into the container contract rather than the agent. The credential claim is the part not yet shown.

Publishers:dev.to

Reality

Evidence58
Adoption20
Hype gap+12
Incentives48
Confidence44
buildOne report1 publisher

A2A holds on the wire. ADK, Strands and Agent Framework are still not substitutable.

One research agent, built three times on three hyperscaler frameworks with the same prompt and the same search tool, diverged in nine ways. None of them were protocol problems.

Publishers:dev.to

Reality

Evidence62
Adoption34
Hype gap+4
Incentives33
Confidence55